Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of...Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of user preferences.To address this,we propose a Conditional Generative Adversarial Network(CGAN)that generates diverse and highly relevant itineraries.Our approach begins by constructing a conditional vector that encapsulates a user’s profile.This vector uniquely fuses embeddings from a Heterogeneous Information Network(HIN)to model complex user-place-route relationships,a Recurrent Neural Network(RNN)to capture sequential path dynamics,and Neural Collaborative Filtering(NCF)to incorporate collaborative signals from the wider user base.This comprehensive condition,further enhanced with features representing user interaction confidence and uncertainty,steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations,effectively mitigating the data sparsity problem.Recommendations are then formulated using an Anchor-and-Expand algorithm,which selects relevant starting Points of Interest(POI)based on user history,then expands routes through latent similarity matching and geographic coherence optimization,culminating in Traveling Salesman Problem(TSP)-based route optimization for practical travel distances.Experiments on a real-world check-in dataset validate our model’s unique generative capability,achieving F1 scores ranging from 0.163 to 0.305,and near-zero pairs−F1 scores between 0.002 and 0.022.These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’past itineraries.This work provides a robust solution for personalized travel planning,capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence.展开更多
The service recommendation mechanism as a key enabling technology that provides users with more proactive and personalized service is one of the important research topics in mobile social network （MSN）. Meanwhile, M...The service recommendation mechanism as a key enabling technology that provides users with more proactive and personalized service is one of the important research topics in mobile social network （MSN）. Meanwhile, MSN is susceptible to various types of anonymous information or hacker actions. Trust can reduce the risk of interaction with unknown entities and prevent malicious attacks. In our paper, we present a trust-based service recommendation algorithm in MSN that considers users＇ similarity and friends＇ familiarity when computing trustworthy neighbors of target users. Firstly, we use the context information and the number of co-rated items to define users＇ similarity. Then, motivated by the theory of six degrees of space, the friend familiarity is derived by graph-based method. Thus the proposed methods are further enhanced by considering users＇ context in the recommendation phase. Finally, a set of simulations are conducted to evaluate the accuracy of the algorithm. The results show that the friend familiarity and user similarity can effectively improve the recommendation performance, and the friend familiarity contributes more than the user similarity.展开更多
Session-based recommendation systems(SBR)are pivotal in suggesting items by analyzing anonymized sequences of user interactions.Traditional methods,while competent,often fall short in two critical areas:they fail to a...Session-based recommendation systems(SBR)are pivotal in suggesting items by analyzing anonymized sequences of user interactions.Traditional methods,while competent,often fall short in two critical areas:they fail to address potential inter-session item transitions,which are behavioral dependencies that extend beyond individual session boundaries,and they rely on monolithic item aggregation to construct session representations.This approach does not capture the multi-scale and heterogeneous nature of user intent,leading to a decrease in modeling accuracy.To overcome these limitations,a novel approach called HMGS has been introduced.This system incorporates dual graph architectures to enhance the recommendation process.A global transition graph captures latent cross-session item dependencies,while a heterogeneous intra-session graph encodesmulti-scale item embeddings through localized feature propagation.Additionally,amulti-tier graphmatchingmechanism aligns user preference signals across different granularities,significantly improving interest localization accuracy.Empirical validation on benchmark datasets(Tmall and Diginetica)confirms HMGS’s efficacy against state-of-the-art baselines.Quantitative analysis reveals performance gains of 20.54%and 12.63%in Precision@10 on Tmall and Diginetica,respectively.Consistent improvements are observed across auxiliary metrics,with MRR@10,Precision@20,and MRR@20 exhibiting enhancements between 4.00%and 21.36%,underscoring the framework’s robustness in multi-faceted recommendation scenarios.展开更多
Recommendation systems(RSs)are crucial in personalizing user experiences in digital environments by suggesting relevant content or items.Collaborative filtering(CF)is a widely used personalization technique that lever...Recommendation systems(RSs)are crucial in personalizing user experiences in digital environments by suggesting relevant content or items.Collaborative filtering(CF)is a widely used personalization technique that leverages user-item interactions to generate recommendations.However,it struggles with challenges like the cold-start problem,scalability issues,and data sparsity.To address these limitations,we develop a Graph Convolutional Networks(GCNs)model that captures the complex network of interactions between users and items,identifying subtle patterns that traditional methods may overlook.We integrate this GCNs model into a federated learning(FL)framework,enabling themodel to learn fromdecentralized datasets.This not only significantly enhances user privacy—a significant improvement over conventionalmodels but also reassures users about the safety of their data.Additionally,by securely incorporating demographic information,our approach further personalizes recommendations and mitigates the coldstart issue without compromising user data.We validate our RSs model using the openMovieLens dataset and evaluate its performance across six key metrics:Precision,Recall,Area Under the Receiver Operating Characteristic Curve(ROC-AUC),F1 Score,Normalized Discounted Cumulative Gain(NDCG),and Mean Reciprocal Rank(MRR).The experimental results demonstrate significant enhancements in recommendation quality,underscoring that combining GCNs with CF in a federated setting provides a transformative solution for advanced recommendation systems.展开更多
To make recommendation on items from the user for historical user rating several intelligent systems are using. The most common method is Recommendation systems. The main areas which play major roles are social networ...To make recommendation on items from the user for historical user rating several intelligent systems are using. The most common method is Recommendation systems. The main areas which play major roles are social networking, digital marketing, online shopping and E-commerce. Recommender system consists of several techniques for recommendations. Here we used the well known approach named as Collaborative filtering (CF). There are two types of problems mainly available with collaborative filtering. They are complete cold start (CCS) problem and incomplete cold start (ICS) problem. The authors proposed three novel methods such as collaborative filtering, and artificial neural networks and at last support vector machine to resolve CCS as well ICS problems. Based on the specific deep neural network SADE we can be able to remove the characteristics of products. By using sequential active of users and product characteristics we have the capability to adapt the cold start product ratings with the applications of the state of the art CF model, time SVD++. The proposed system consists of Netflix rating dataset which is used to perform the baseline techniques for rating prediction of cold start items. The calculation of two proposed recommendation techniques is compared on ICS items, and it is proved that it will be adaptable method. The proposed method can be able to transfer the products since cold start transfers to non-cold start status. Artificial Neural Network (ANN) is employed here to extract the item content features. One of the user preferences such as temporal dynamics is used to obtain the contented characteristics into predictions to overcome those problems. For the process of classification we have used linear support vector machine classifiers to receive the better performance when compared with the earlier methods.展开更多
With the rapid growth of manuscript submissions,finding eligible reviewers for every submission has become a heavy task.Recommender systems are powerful tools developed in computer science and information science to d...With the rapid growth of manuscript submissions,finding eligible reviewers for every submission has become a heavy task.Recommender systems are powerful tools developed in computer science and information science to deal with this problem.However,most existing approaches resort to text mining techniques to match manuscripts with potential reviewers,which require high-quality textual information to perform well.In this paper,we propose a reviewer recommendation algorithm based on a network diffusion process on a scholar-paper multilayer network,with no requirement for textual information.The network incorporates the relationship of scholar-paper pairs,the collaboration among scholars,and the bibliographic coupling among papers.Experimental results show that our proposed algorithm outperforms other state-of-the-art recommendation methods that use graph random walk and matrix factorization and methods that use machine learning and natural language processing,with improvements of over 7.62%in recall,5.66%in hit rate,and 47.53%in ranking score.Our work sheds light on the effectiveness of multilayer network diffusion-based methods in the reviewer recommendation problem,which will help to facilitate the peer-review process and promote information retrieval research in other practical scenes.展开更多
On Twitter,people often use hashtags to mark the subject of a tweet.Tweets have specific themes or content that are easy for people to manage.With the increase in the number of tweets,how to automatically recommend ha...On Twitter,people often use hashtags to mark the subject of a tweet.Tweets have specific themes or content that are easy for people to manage.With the increase in the number of tweets,how to automatically recommend hashtags for tweets has received wide attention.The previous hashtag recommendation methods were to convert the task into a multi-class classification problem.However,these methods can only recommend hashtags that appeared in historical information,and cannot recommend the new ones.In this work,we extend the self-attention mechanism to turn the hashtag recommendation task into a sequence labeling task.To train and evaluate the proposed method,we used the real tweet data which is collected from Twitter.Experimental results show that the proposed method can be significantly better than the most advanced method.Compared with the state-of-the-art methods,the accuracy of our method has been increased 4%.展开更多
Purpose:Based on real-world academic data,this study aims to use network embedding technology to mining academic relationships,and investigate the effectiveness of the proposed embedding model on academic collaborator...Purpose:Based on real-world academic data,this study aims to use network embedding technology to mining academic relationships,and investigate the effectiveness of the proposed embedding model on academic collaborator recommendation tasks.Design/methodology/approach:We propose an academic collaborator recommendation model based on attributed network embedding(ACR-ANE),which can get enhanced scholar embedding and take full advantage of the topological structure of the network and multi-type scholar attributes.The non-local neighbors for scholars are defined to capture strong relationships among scholars.A deep auto-encoder is adopted to encode the academic collaboration network structure and scholar attributes into a low-dimensional representation space.Findings:1.The proposed non-local neighbors can better describe the relationships among scholars in the real world than the first-order neighbors.2.It is important to consider the structure of the academic collaboration network and scholar attributes when recommending collaborators for scholars simultaneously.Research limitations:The designed method works for static networks,without taking account of the network dynamics.Practical implications:The designed model is embedded in academic collaboration network structure and scholarly attributes,which can be used to help scholars recommend potential collaborators.Originality/value:Experiments on two real-world scholarly datasets,Aminer and APS,show that our proposed method performs better than other baselines.展开更多
ExpertRecommendation(ER)aims to identify domain experts with high expertise and willingness to provide answers to questions in Community Question Answering(CQA)web services.How to model questions and users in the hete...ExpertRecommendation(ER)aims to identify domain experts with high expertise and willingness to provide answers to questions in Community Question Answering(CQA)web services.How to model questions and users in the heterogeneous content network is critical to this task.Most traditional methods focus on modeling questions and users based on the textual content left in the community while ignoring the structural properties of heterogeneous CQA networks and always suffering from textual data sparsity issues.Recent approaches take advantage of structural proximities between nodes and attempt to fuse the textual content of nodes for modeling.However,they often fail to distinguish the nodes’personalized preferences and only consider the textual content of a part of the nodes in network embedding learning,while ignoring the semantic relevance of nodes.In this paper,we propose a novel framework that jointly considers the structural proximity relations and textual semantic relevance to model users and questions more comprehensively.Specifically,we learn topology-based embeddings through a hierarchical attentive network learning strategy,in which the proximity information and the personalized preference of nodes are encoded and preserved.Meanwhile,we utilize the node’s textual content and the text correlation between adjacent nodes to build the content-based embedding through a meta-context-aware skip-gram model.In addition,the user’s relative answer quality is incorporated to promote the ranking performance.Experimental results show that our proposed framework consistently and significantly outperforms the state-of-the-art baselines on three real-world datasets by taking the deep semantic understanding and structural feature learning together.The performance of the proposed work is analyzed in terms of MRR,P@K,and MAP and is proven to be more advanced than the existing methodologies.展开更多
GitHub repository recommendation is a research hotspot in the field of open-source software. The current problemswith the repository recommendation systemare the insufficient utilization of open-source community infor...GitHub repository recommendation is a research hotspot in the field of open-source software. The current problemswith the repository recommendation systemare the insufficient utilization of open-source community informationand the fact that the scoring metrics used to calculate the matching degree between developers and repositoriesare developed manually and rely too much on human experience, leading to poor recommendation results. Toaddress these problems, we design a questionnaire to investigate which repository information developers focus onand propose a graph convolutional network-based repository recommendation system (GCNRec). First, to solveinsufficient information utilization in open-source communities, we construct a Developer-Repository networkusing four types of behavioral data that best reflect developers’ programming preferences and extract features ofdevelopers and repositories from the repository content that developers focus on. Then, we design a repositoryrecommendation model based on a multi-layer graph convolutional network to avoid the manual formulation ofscoringmetrics. Thismodel takes the Developer-Repository network, developer features and repository features asinputs, and recommends the top-k repositories that developers are most likely to be interested in by learning theirpreferences. We have verified the proposed GCNRec on the dataset, and by comparing it with other open-sourcerepository recommendation methods, GCNRec achieves higher precision and hit rate.展开更多
In the era of exponential growth of digital information,recommender algorithms are vital for helping users navigate vast data to find relevant items.Traditional approaches such as collaborative filtering and contentba...In the era of exponential growth of digital information,recommender algorithms are vital for helping users navigate vast data to find relevant items.Traditional approaches such as collaborative filtering and contentbasedmethods have limitations in capturing complex,multi-faceted relationships in large-scale,sparse datasets.Recent advances in Graph Neural Networks(GNNs)have significantly improved recommendation performance by modeling high-order connection patterns within user-item interaction networks.However,existing GNN-based models like LightGCN and NGCF focus primarily on single-type interactions and often overlook diverse semantic relationships,leading to reduced recommendation diversity and limited generalization.To address these challenges,this paper proposes a dual multi-relational graph neural network recommendation algorithm based on relational interactions.Our approach constructs two complementary graph structures:a User-Item Interaction Graph(UIIG),which explicitly models direct user behaviors such as clicks and purchases,and a Relational Association Graph(RAG),which uncovers latent associations based on user similarities and item attributes.The proposed Dual Multi-relational Graph Neural Network(DMGNN)features two parallel branches that perform multi-layer graph convolutional operations,followed by an adaptive fusion mechanism to effectively integrate information from both graphs.This design enhances the model’s capacity to capture diverse relationship types and complex relational patterns.Extensive experiments conducted on benchmark datasets—including MovieLens-1M,Amazon-Electronics,and Yelp—demonstrate thatDMGNN outperforms state-of-the-art baselines,achieving improvements of up to 12.3%in Precision,9.7%in Recall,and 11.5%in F1 score.Moreover,DMGNN significantly boosts recommendation diversity by 15.2%,balancing accuracy with exploration.These results highlight the effectiveness of leveraging hierarchical multi-relational information,offering a promising solution to the challenges of data sparsity and relation heterogeneity in recommendation systems.Our work advances the theoretical understanding of multi-relational graph modeling and presents practical insights for developing more personalized,diverse,and robust recommender systems.展开更多
Sequential recommendation based on amulti-interest framework aims to analyze different aspects of interest based on historical interactions and generate predictions of a user’s potential interest in a list of items.M...Sequential recommendation based on amulti-interest framework aims to analyze different aspects of interest based on historical interactions and generate predictions of a user’s potential interest in a list of items.Most existing methods only focus on what are themultiple interests behind interactions but neglect the evolution of user interests over time.To explore the impact of temporal dynamics on interest extraction,this paper explicitly models the timestamp with amulti-interest network and proposes a time-highlighted network to learn user preferences,which considers not only the interests at different moments but also the possible trends of interest over time.More specifically,the time intervals between historical interactions and prediction moments are first mapped to vectors.Meanwhile,a time-attentive aggregation layer is designed to capture the trends of items in the sequence over time,where the time intervals are seen as additional information to distinguish the importance of different neighbors.Then,the learned items’transition trends are aggregated with the items themselves by a gated unit.Finally,a self-attention network is deployed to capture multiple interests with the obtained temporal information vectors.Extensive experiments are carried out based on three real-world datasets and the results convincingly establish the superiority of the proposed method over other state-of-the-art baselines in terms of model performance.展开更多
Session-based Recommendation(SBR)aims to accurately recom-mend a list of items to users based on anonymous historical session sequences.Existing methods for SBR suffer from several limitations:SBR based on Graph Neura...Session-based Recommendation(SBR)aims to accurately recom-mend a list of items to users based on anonymous historical session sequences.Existing methods for SBR suffer from several limitations:SBR based on Graph Neural Network often has information loss when constructing session graphs;Inadequate consideration is given to influencing factors,such as item price,and users’dynamic interest evolution is not taken into account.A new session recommendation model called Price-aware Session-based Recommendation(PASBR)is proposed to address these limitations.PASBR constructs session graphs by information lossless approaches to fully encode the original session information,then introduces item price as a new factor and models users’price tolerance for various items to influence users’preferences.In addition,PASBR proposes a new method to encode user intent at the item category level and tries to capture the dynamic interest of users over time.Finally,PASBR fuses the multi-perspective features to generate the global representation of users and make a prediction.Specifically,the intent,the short-term and long-term interests,and the dynamic interests of a user are combined.Experiments on two real-world datasets show that PASBR can outperform representative baselines for SBR.展开更多
A large number of Web APIs have been released as services in mobile communications,but the service provided by a single Web API is usually limited.To enrich the services in mobile communications,developers have combin...A large number of Web APIs have been released as services in mobile communications,but the service provided by a single Web API is usually limited.To enrich the services in mobile communications,developers have combined Web APIs and developed a new service,which is known as a mashup.The emergence of mashups greatly increases the number of services in mobile communications,especially in mobile networks and the Internet-of-Things(IoT),and has encouraged companies and individuals to develop even more mashups,which has led to the dramatic increase in the number of mashups.Such a trend brings with it big data,such as the massive text data from the mashups themselves and continually-generated usage data.Thus,the question of how to determine the most suitable mashups from big data has become a challenging problem.In this paper,we propose a mashup recommendation framework from big data in mobile networks and the IoT.The proposed framework is driven by machine learning techniques,including neural embedding,clustering,and matrix factorization.We employ neural embedding to learn the distributed representation of mashups and propose to use cluster analysis to learn the relationship among the mashups.We also develop a novel Joint Matrix Factorization(JMF)model to complete the mashup recommendation task,where we design a new objective function and an optimization algorithm.We then crawl through a real-world large mashup dataset and perform experiments.The experimental results demonstrate that our framework achieves high accuracy in mashup recommendation and performs better than all compared baselines.展开更多
The relationship between users and items,which cannot be recovered by traditional techniques,can be extracted by the recommendation algorithm based on the graph convolution network.The current simple linear combinatio...The relationship between users and items,which cannot be recovered by traditional techniques,can be extracted by the recommendation algorithm based on the graph convolution network.The current simple linear combination of these algorithms may not be sufficient to extract the complex structure of user interaction data.This paper presents a new approach to address such issues,utilizing the graph convolution network to extract association relations.The proposed approach mainly includes three modules:Embedding layer,forward propagation layer,and score prediction layer.The embedding layer models users and items according to their interaction information and generates initial feature vectors as input for the forward propagation layer.The forward propagation layer designs two parallel graph convolution networks with self-connections,which extract higher-order association relevance from users and items separately by multi-layer graph convolution.Furthermore,the forward propagation layer integrates the attention factor to assign different weights among the hop neighbors of the graph convolution network fusion,capturing more comprehensive association relevance between users and items as input for the score prediction layer.The score prediction layer introduces MLP(multi-layer perceptron)to conduct non-linear feature interaction between users and items,respectively.Finally,the prediction score of users to items is obtained.The recall rate and normalized discounted cumulative gain were used as evaluation indexes.The proposed approach effectively integrates higher-order information in user entries,and experimental analysis demonstrates its superiority over the existing algorithms.展开更多
Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been ...Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.展开更多
We search a variety of things over the Internet in our daily lives, and numerous search engines are available to get us more relevant results. With the rapid technological advancement, the internet has become a major ...We search a variety of things over the Internet in our daily lives, and numerous search engines are available to get us more relevant results. With the rapid technological advancement, the internet has become a major source of obtaining information. Further, the advent of the Web2.0 era has led to an increased interaction between the user and the website. It has become challenging to provide information to users as per their interests. Because of copyright restrictions, most of existing research studies are confronting the lack of availability of the content of candidates recommending articles. The content of such articles is not always available freely and hence leads to inadequate recommendation results. Moreover, various research studies base recommendation on user profiles. Therefore, their recommendation needs a significant number of registered users in the system. In recent years, research work proves that Knowledge graphs have yielded better in generating quality recommendation results and alleviating sparsity and cold start issues. Network embedding techniques try to learn high quality feature vectors automatically from network structures, enabling vector-based measurers of node relatedness. Keeping the strength of Network embedding techniques, the proposed citation-based recommendation approach makes use of heterogeneous network embedding in generating recommendation results. The novelty of this paper is in exploiting the performance of a network embedding approach i.e., matapath2vec to generate paper recommendations. Unlike existing approaches, the proposed method has the capability of learning low-dimensional latent representation of nodes (i.e., research papers) in a network. We apply metapath2vec on a knowledge network built by the ACL Anthology Network (all about NLP) and use the node relatedness to generate item (research article) recommendations.展开更多
Although content caching and recommendation are two complementary approaches to improve the user experience,it is still challenging to provide an integrated paradigm to fully explore their potential,due to the high co...Although content caching and recommendation are two complementary approaches to improve the user experience,it is still challenging to provide an integrated paradigm to fully explore their potential,due to the high complexity and complicated tradeoff relationship.To provide an efficient management framework,the joint design of content delivery and recommendation in wireless content caching networks is studied in this paper.First,a joint transmission scheme of content objects and recommendation lists is designed with edge caching,and an optimization problem is formulated to balance the utility and cost of content caching and recommendation,which is an mixed integer nonlinear programming problem.Second,a reinforcement learning based algorithm is proposed to implement real time management of content caching,recommendation and delivery,which can approach the optimal solution without iterations during each decision epoch.Finally,the simulation results are provided to evaluate the performance of our proposed scheme,which show that it can achieve lower cost than the existing content caching and recommendation schemes.展开更多
In software development projects,bugs are common phenomena.Developers report bugs in open source repositories.There is a need to develop high quality developer prediction model that considers developer work satisfacti...In software development projects,bugs are common phenomena.Developers report bugs in open source repositories.There is a need to develop high quality developer prediction model that considers developer work satisfaction,keep within limited development cost,and improve bug resolution time.To address and resolve bug report as soon as possible is the main focus of triager when a new bug is reported.Thus,developer work efficiency is an important factor in bug-fixing.To address these issues,a proposed approach recommends a set of developers that could potentially share their knowledge with each other to fix new bug reports.The proposed approach is called developer working efficiency and social network based developer recommendation(DweSn).It is a composite model that builds developers'profile by using developer average bug fixing time,work efficiency to fix variety of bugs,as well as the developer's social interactions with other developers.A similarity measure is applied between new bug and bugs in corpus to extract the list of capable developers from the corpus.The proposed approach only selects those developers who are active and less loaded with work.The developer with the highest profile score is assigned the bugs.We evaluated our approach on the subset of five large open-source projects including Mozilla,Netbeans,Eclipse,Firefox and OpenOffice,and compared it with the state-of-the-art.The results demonstrate that combination of developers'efficiency with their average bug fixing time and interactions in their social network gives good accuracy and efficiently reduces bug tossing length.This approach shows an improvement in prediction accuracy,precision,recall,F-score and reduced bug tossing length up to 93.89%,93.12%,93.46%,93.27%and 93.25%,respectively.The proposed approach achieved a 93%hit ratio and 93.34%mean reciprocal rank,indicating that our proposed triager is able to efficiently assign bugs to correct developers.展开更多
The recommendation system(RS)on the strength of Graph Neural Networks(GNN)perceives a user-item interaction graph after collecting all items the user has interacted with.Afterward the RS performs neighborhood aggregat...The recommendation system(RS)on the strength of Graph Neural Networks(GNN)perceives a user-item interaction graph after collecting all items the user has interacted with.Afterward the RS performs neighborhood aggregation on the graph to generate long-term preference representations for the user in quick succession.However,user preferences are dynamic.With the passage of time and some trend guidance,users may generate some short-term preferences,which are more likely to lead to user-item interactions.A GNN recommendation based on long-and short-term preference(LSGNN)is proposed to address the above problems.LSGNN consists of four modules,using a GNN combined with the attention mechanism to extract long-term preference features,using Bidirectional Encoder Representation from Transformers(BERT)and the attention mechanism combined with Bi-Directional Gated Recurrent Unit(Bi-GRU)to extract short-term preference features,using Convolutional Neural Network(CNN)combined with the attention mechanism to add title and description representations of items,finally inner-producing long-term and short-term preference features as well as features of items to achieve recommendations.In experiments conducted on five publicly available datasets from Amazon,LSGNN is superior to state-of-the-art personalized recommendation techniques.展开更多
基金supported by the Chung-Ang University Research Grants in 2023.Alsothe work is supported by the ELLIIT Excellence Center at Linköping–Lund in Information Technology in Sweden.
文摘Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of user preferences.To address this,we propose a Conditional Generative Adversarial Network(CGAN)that generates diverse and highly relevant itineraries.Our approach begins by constructing a conditional vector that encapsulates a user’s profile.This vector uniquely fuses embeddings from a Heterogeneous Information Network(HIN)to model complex user-place-route relationships,a Recurrent Neural Network(RNN)to capture sequential path dynamics,and Neural Collaborative Filtering(NCF)to incorporate collaborative signals from the wider user base.This comprehensive condition,further enhanced with features representing user interaction confidence and uncertainty,steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations,effectively mitigating the data sparsity problem.Recommendations are then formulated using an Anchor-and-Expand algorithm,which selects relevant starting Points of Interest(POI)based on user history,then expands routes through latent similarity matching and geographic coherence optimization,culminating in Traveling Salesman Problem(TSP)-based route optimization for practical travel distances.Experiments on a real-world check-in dataset validate our model’s unique generative capability,achieving F1 scores ranging from 0.163 to 0.305,and near-zero pairs−F1 scores between 0.002 and 0.022.These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’past itineraries.This work provides a robust solution for personalized travel planning,capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence.
基金Supported by the National Natural Science Foundation of China(71662014 and 61602219)the Natural Science Foundation of Jiangxi Province of China(20132BAB201050)the Science and Technology Project of Jiangxi Province Educational Department(GJJ151601)
文摘The service recommendation mechanism as a key enabling technology that provides users with more proactive and personalized service is one of the important research topics in mobile social network （MSN）. Meanwhile, MSN is susceptible to various types of anonymous information or hacker actions. Trust can reduce the risk of interaction with unknown entities and prevent malicious attacks. In our paper, we present a trust-based service recommendation algorithm in MSN that considers users＇ similarity and friends＇ familiarity when computing trustworthy neighbors of target users. Firstly, we use the context information and the number of co-rated items to define users＇ similarity. Then, motivated by the theory of six degrees of space, the friend familiarity is derived by graph-based method. Thus the proposed methods are further enhanced by considering users＇ context in the recommendation phase. Finally, a set of simulations are conducted to evaluate the accuracy of the algorithm. The results show that the friend familiarity and user similarity can effectively improve the recommendation performance, and the friend familiarity contributes more than the user similarity.
基金funded by the State Grid Hebei Electric Power Company(Project Number:KJ2023-093).
文摘Session-based recommendation systems(SBR)are pivotal in suggesting items by analyzing anonymized sequences of user interactions.Traditional methods,while competent,often fall short in two critical areas:they fail to address potential inter-session item transitions,which are behavioral dependencies that extend beyond individual session boundaries,and they rely on monolithic item aggregation to construct session representations.This approach does not capture the multi-scale and heterogeneous nature of user intent,leading to a decrease in modeling accuracy.To overcome these limitations,a novel approach called HMGS has been introduced.This system incorporates dual graph architectures to enhance the recommendation process.A global transition graph captures latent cross-session item dependencies,while a heterogeneous intra-session graph encodesmulti-scale item embeddings through localized feature propagation.Additionally,amulti-tier graphmatchingmechanism aligns user preference signals across different granularities,significantly improving interest localization accuracy.Empirical validation on benchmark datasets(Tmall and Diginetica)confirms HMGS’s efficacy against state-of-the-art baselines.Quantitative analysis reveals performance gains of 20.54%and 12.63%in Precision@10 on Tmall and Diginetica,respectively.Consistent improvements are observed across auxiliary metrics,with MRR@10,Precision@20,and MRR@20 exhibiting enhancements between 4.00%and 21.36%,underscoring the framework’s robustness in multi-faceted recommendation scenarios.
基金funded by Soonchunhyang University,Grant Numbers 20241422BK21 FOUR(Fostering Outstanding Universities for Research,Grant Number 5199990914048).
文摘Recommendation systems(RSs)are crucial in personalizing user experiences in digital environments by suggesting relevant content or items.Collaborative filtering(CF)is a widely used personalization technique that leverages user-item interactions to generate recommendations.However,it struggles with challenges like the cold-start problem,scalability issues,and data sparsity.To address these limitations,we develop a Graph Convolutional Networks(GCNs)model that captures the complex network of interactions between users and items,identifying subtle patterns that traditional methods may overlook.We integrate this GCNs model into a federated learning(FL)framework,enabling themodel to learn fromdecentralized datasets.This not only significantly enhances user privacy—a significant improvement over conventionalmodels but also reassures users about the safety of their data.Additionally,by securely incorporating demographic information,our approach further personalizes recommendations and mitigates the coldstart issue without compromising user data.We validate our RSs model using the openMovieLens dataset and evaluate its performance across six key metrics:Precision,Recall,Area Under the Receiver Operating Characteristic Curve(ROC-AUC),F1 Score,Normalized Discounted Cumulative Gain(NDCG),and Mean Reciprocal Rank(MRR).The experimental results demonstrate significant enhancements in recommendation quality,underscoring that combining GCNs with CF in a federated setting provides a transformative solution for advanced recommendation systems.
文摘To make recommendation on items from the user for historical user rating several intelligent systems are using. The most common method is Recommendation systems. The main areas which play major roles are social networking, digital marketing, online shopping and E-commerce. Recommender system consists of several techniques for recommendations. Here we used the well known approach named as Collaborative filtering (CF). There are two types of problems mainly available with collaborative filtering. They are complete cold start (CCS) problem and incomplete cold start (ICS) problem. The authors proposed three novel methods such as collaborative filtering, and artificial neural networks and at last support vector machine to resolve CCS as well ICS problems. Based on the specific deep neural network SADE we can be able to remove the characteristics of products. By using sequential active of users and product characteristics we have the capability to adapt the cold start product ratings with the applications of the state of the art CF model, time SVD++. The proposed system consists of Netflix rating dataset which is used to perform the baseline techniques for rating prediction of cold start items. The calculation of two proposed recommendation techniques is compared on ICS items, and it is proved that it will be adaptable method. The proposed method can be able to transfer the products since cold start transfers to non-cold start status. Artificial Neural Network (ANN) is employed here to extract the item content features. One of the user preferences such as temporal dynamics is used to obtain the contented characteristics into predictions to overcome those problems. For the process of classification we have used linear support vector machine classifiers to receive the better performance when compared with the earlier methods.
基金Project supported by the National Natural Science Foundation of China(Grant No.T2293771)the New Cornerstone Science Foundation through the XPLORER PRIZE.
文摘With the rapid growth of manuscript submissions,finding eligible reviewers for every submission has become a heavy task.Recommender systems are powerful tools developed in computer science and information science to deal with this problem.However,most existing approaches resort to text mining techniques to match manuscripts with potential reviewers,which require high-quality textual information to perform well.In this paper,we propose a reviewer recommendation algorithm based on a network diffusion process on a scholar-paper multilayer network,with no requirement for textual information.The network incorporates the relationship of scholar-paper pairs,the collaboration among scholars,and the bibliographic coupling among papers.Experimental results show that our proposed algorithm outperforms other state-of-the-art recommendation methods that use graph random walk and matrix factorization and methods that use machine learning and natural language processing,with improvements of over 7.62%in recall,5.66%in hit rate,and 47.53%in ranking score.Our work sheds light on the effectiveness of multilayer network diffusion-based methods in the reviewer recommendation problem,which will help to facilitate the peer-review process and promote information retrieval research in other practical scenes.
文摘On Twitter,people often use hashtags to mark the subject of a tweet.Tweets have specific themes or content that are easy for people to manage.With the increase in the number of tweets,how to automatically recommend hashtags for tweets has received wide attention.The previous hashtag recommendation methods were to convert the task into a multi-class classification problem.However,these methods can only recommend hashtags that appeared in historical information,and cannot recommend the new ones.In this work,we extend the self-attention mechanism to turn the hashtag recommendation task into a sequence labeling task.To train and evaluate the proposed method,we used the real tweet data which is collected from Twitter.Experimental results show that the proposed method can be significantly better than the most advanced method.Compared with the state-of-the-art methods,the accuracy of our method has been increased 4%.
基金supported by National Natural Science Foundation of China(No.61603310)the Fundamental Research Funds for the Central Universities(No.XDJK2018B019).
文摘Purpose:Based on real-world academic data,this study aims to use network embedding technology to mining academic relationships,and investigate the effectiveness of the proposed embedding model on academic collaborator recommendation tasks.Design/methodology/approach:We propose an academic collaborator recommendation model based on attributed network embedding(ACR-ANE),which can get enhanced scholar embedding and take full advantage of the topological structure of the network and multi-type scholar attributes.The non-local neighbors for scholars are defined to capture strong relationships among scholars.A deep auto-encoder is adopted to encode the academic collaboration network structure and scholar attributes into a low-dimensional representation space.Findings:1.The proposed non-local neighbors can better describe the relationships among scholars in the real world than the first-order neighbors.2.It is important to consider the structure of the academic collaboration network and scholar attributes when recommending collaborators for scholars simultaneously.Research limitations:The designed method works for static networks,without taking account of the network dynamics.Practical implications:The designed model is embedded in academic collaboration network structure and scholarly attributes,which can be used to help scholars recommend potential collaborators.Originality/value:Experiments on two real-world scholarly datasets,Aminer and APS,show that our proposed method performs better than other baselines.
文摘ExpertRecommendation(ER)aims to identify domain experts with high expertise and willingness to provide answers to questions in Community Question Answering(CQA)web services.How to model questions and users in the heterogeneous content network is critical to this task.Most traditional methods focus on modeling questions and users based on the textual content left in the community while ignoring the structural properties of heterogeneous CQA networks and always suffering from textual data sparsity issues.Recent approaches take advantage of structural proximities between nodes and attempt to fuse the textual content of nodes for modeling.However,they often fail to distinguish the nodes’personalized preferences and only consider the textual content of a part of the nodes in network embedding learning,while ignoring the semantic relevance of nodes.In this paper,we propose a novel framework that jointly considers the structural proximity relations and textual semantic relevance to model users and questions more comprehensively.Specifically,we learn topology-based embeddings through a hierarchical attentive network learning strategy,in which the proximity information and the personalized preference of nodes are encoded and preserved.Meanwhile,we utilize the node’s textual content and the text correlation between adjacent nodes to build the content-based embedding through a meta-context-aware skip-gram model.In addition,the user’s relative answer quality is incorporated to promote the ranking performance.Experimental results show that our proposed framework consistently and significantly outperforms the state-of-the-art baselines on three real-world datasets by taking the deep semantic understanding and structural feature learning together.The performance of the proposed work is analyzed in terms of MRR,P@K,and MAP and is proven to be more advanced than the existing methodologies.
基金supported by Special Funds for the Construction of an Innovative Province of Hunan,No.2020GK2028.
文摘GitHub repository recommendation is a research hotspot in the field of open-source software. The current problemswith the repository recommendation systemare the insufficient utilization of open-source community informationand the fact that the scoring metrics used to calculate the matching degree between developers and repositoriesare developed manually and rely too much on human experience, leading to poor recommendation results. Toaddress these problems, we design a questionnaire to investigate which repository information developers focus onand propose a graph convolutional network-based repository recommendation system (GCNRec). First, to solveinsufficient information utilization in open-source communities, we construct a Developer-Repository networkusing four types of behavioral data that best reflect developers’ programming preferences and extract features ofdevelopers and repositories from the repository content that developers focus on. Then, we design a repositoryrecommendation model based on a multi-layer graph convolutional network to avoid the manual formulation ofscoringmetrics. Thismodel takes the Developer-Repository network, developer features and repository features asinputs, and recommends the top-k repositories that developers are most likely to be interested in by learning theirpreferences. We have verified the proposed GCNRec on the dataset, and by comparing it with other open-sourcerepository recommendation methods, GCNRec achieves higher precision and hit rate.
文摘In the era of exponential growth of digital information,recommender algorithms are vital for helping users navigate vast data to find relevant items.Traditional approaches such as collaborative filtering and contentbasedmethods have limitations in capturing complex,multi-faceted relationships in large-scale,sparse datasets.Recent advances in Graph Neural Networks(GNNs)have significantly improved recommendation performance by modeling high-order connection patterns within user-item interaction networks.However,existing GNN-based models like LightGCN and NGCF focus primarily on single-type interactions and often overlook diverse semantic relationships,leading to reduced recommendation diversity and limited generalization.To address these challenges,this paper proposes a dual multi-relational graph neural network recommendation algorithm based on relational interactions.Our approach constructs two complementary graph structures:a User-Item Interaction Graph(UIIG),which explicitly models direct user behaviors such as clicks and purchases,and a Relational Association Graph(RAG),which uncovers latent associations based on user similarities and item attributes.The proposed Dual Multi-relational Graph Neural Network(DMGNN)features two parallel branches that perform multi-layer graph convolutional operations,followed by an adaptive fusion mechanism to effectively integrate information from both graphs.This design enhances the model’s capacity to capture diverse relationship types and complex relational patterns.Extensive experiments conducted on benchmark datasets—including MovieLens-1M,Amazon-Electronics,and Yelp—demonstrate thatDMGNN outperforms state-of-the-art baselines,achieving improvements of up to 12.3%in Precision,9.7%in Recall,and 11.5%in F1 score.Moreover,DMGNN significantly boosts recommendation diversity by 15.2%,balancing accuracy with exploration.These results highlight the effectiveness of leveraging hierarchical multi-relational information,offering a promising solution to the challenges of data sparsity and relation heterogeneity in recommendation systems.Our work advances the theoretical understanding of multi-relational graph modeling and presents practical insights for developing more personalized,diverse,and robust recommender systems.
基金supported in part by the National Natural Science Foundation of China under Grant 61702060.
文摘Sequential recommendation based on amulti-interest framework aims to analyze different aspects of interest based on historical interactions and generate predictions of a user’s potential interest in a list of items.Most existing methods only focus on what are themultiple interests behind interactions but neglect the evolution of user interests over time.To explore the impact of temporal dynamics on interest extraction,this paper explicitly models the timestamp with amulti-interest network and proposes a time-highlighted network to learn user preferences,which considers not only the interests at different moments but also the possible trends of interest over time.More specifically,the time intervals between historical interactions and prediction moments are first mapped to vectors.Meanwhile,a time-attentive aggregation layer is designed to capture the trends of items in the sequence over time,where the time intervals are seen as additional information to distinguish the importance of different neighbors.Then,the learned items’transition trends are aggregated with the items themselves by a gated unit.Finally,a self-attention network is deployed to capture multiple interests with the obtained temporal information vectors.Extensive experiments are carried out based on three real-world datasets and the results convincingly establish the superiority of the proposed method over other state-of-the-art baselines in terms of model performance.
文摘Session-based Recommendation(SBR)aims to accurately recom-mend a list of items to users based on anonymous historical session sequences.Existing methods for SBR suffer from several limitations:SBR based on Graph Neural Network often has information loss when constructing session graphs;Inadequate consideration is given to influencing factors,such as item price,and users’dynamic interest evolution is not taken into account.A new session recommendation model called Price-aware Session-based Recommendation(PASBR)is proposed to address these limitations.PASBR constructs session graphs by information lossless approaches to fully encode the original session information,then introduces item price as a new factor and models users’price tolerance for various items to influence users’preferences.In addition,PASBR proposes a new method to encode user intent at the item category level and tries to capture the dynamic interest of users over time.Finally,PASBR fuses the multi-perspective features to generate the global representation of users and make a prediction.Specifically,the intent,the short-term and long-term interests,and the dynamic interests of a user are combined.Experiments on two real-world datasets show that PASBR can outperform representative baselines for SBR.
基金supported by the National Key R&D Program of China (No.2021YFF0901002)the National Natural Science Foundation of China (No.61802291)+1 种基金Fundamental Research Funds for the Provincial Universities of Zhejiang (GK199900299012-025)Fundamental Research Funds for the Central Universities (No.JB210311).
文摘A large number of Web APIs have been released as services in mobile communications,but the service provided by a single Web API is usually limited.To enrich the services in mobile communications,developers have combined Web APIs and developed a new service,which is known as a mashup.The emergence of mashups greatly increases the number of services in mobile communications,especially in mobile networks and the Internet-of-Things(IoT),and has encouraged companies and individuals to develop even more mashups,which has led to the dramatic increase in the number of mashups.Such a trend brings with it big data,such as the massive text data from the mashups themselves and continually-generated usage data.Thus,the question of how to determine the most suitable mashups from big data has become a challenging problem.In this paper,we propose a mashup recommendation framework from big data in mobile networks and the IoT.The proposed framework is driven by machine learning techniques,including neural embedding,clustering,and matrix factorization.We employ neural embedding to learn the distributed representation of mashups and propose to use cluster analysis to learn the relationship among the mashups.We also develop a novel Joint Matrix Factorization(JMF)model to complete the mashup recommendation task,where we design a new objective function and an optimization algorithm.We then crawl through a real-world large mashup dataset and perform experiments.The experimental results demonstrate that our framework achieves high accuracy in mashup recommendation and performs better than all compared baselines.
基金supported by the Fundamental Research Funds for Higher Education Institutions of Heilongjiang Province(145209126)the Heilongjiang Province Higher Education Teaching Reform Project under Grant No.SJGY20200770.
文摘The relationship between users and items,which cannot be recovered by traditional techniques,can be extracted by the recommendation algorithm based on the graph convolution network.The current simple linear combination of these algorithms may not be sufficient to extract the complex structure of user interaction data.This paper presents a new approach to address such issues,utilizing the graph convolution network to extract association relations.The proposed approach mainly includes three modules:Embedding layer,forward propagation layer,and score prediction layer.The embedding layer models users and items according to their interaction information and generates initial feature vectors as input for the forward propagation layer.The forward propagation layer designs two parallel graph convolution networks with self-connections,which extract higher-order association relevance from users and items separately by multi-layer graph convolution.Furthermore,the forward propagation layer integrates the attention factor to assign different weights among the hop neighbors of the graph convolution network fusion,capturing more comprehensive association relevance between users and items as input for the score prediction layer.The score prediction layer introduces MLP(multi-layer perceptron)to conduct non-linear feature interaction between users and items,respectively.Finally,the prediction score of users to items is obtained.The recall rate and normalized discounted cumulative gain were used as evaluation indexes.The proposed approach effectively integrates higher-order information in user entries,and experimental analysis demonstrates its superiority over the existing algorithms.
基金This work was supported by the Kyonggi University Research Grant 2022.
文摘Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.
文摘We search a variety of things over the Internet in our daily lives, and numerous search engines are available to get us more relevant results. With the rapid technological advancement, the internet has become a major source of obtaining information. Further, the advent of the Web2.0 era has led to an increased interaction between the user and the website. It has become challenging to provide information to users as per their interests. Because of copyright restrictions, most of existing research studies are confronting the lack of availability of the content of candidates recommending articles. The content of such articles is not always available freely and hence leads to inadequate recommendation results. Moreover, various research studies base recommendation on user profiles. Therefore, their recommendation needs a significant number of registered users in the system. In recent years, research work proves that Knowledge graphs have yielded better in generating quality recommendation results and alleviating sparsity and cold start issues. Network embedding techniques try to learn high quality feature vectors automatically from network structures, enabling vector-based measurers of node relatedness. Keeping the strength of Network embedding techniques, the proposed citation-based recommendation approach makes use of heterogeneous network embedding in generating recommendation results. The novelty of this paper is in exploiting the performance of a network embedding approach i.e., matapath2vec to generate paper recommendations. Unlike existing approaches, the proposed method has the capability of learning low-dimensional latent representation of nodes (i.e., research papers) in a network. We apply metapath2vec on a knowledge network built by the ACL Anthology Network (all about NLP) and use the node relatedness to generate item (research article) recommendations.
基金supported by Beijing Natural Science Foundation(Grant L182039),and National Natural Science Foundation of China(Grant 61971061).
文摘Although content caching and recommendation are two complementary approaches to improve the user experience,it is still challenging to provide an integrated paradigm to fully explore their potential,due to the high complexity and complicated tradeoff relationship.To provide an efficient management framework,the joint design of content delivery and recommendation in wireless content caching networks is studied in this paper.First,a joint transmission scheme of content objects and recommendation lists is designed with edge caching,and an optimization problem is formulated to balance the utility and cost of content caching and recommendation,which is an mixed integer nonlinear programming problem.Second,a reinforcement learning based algorithm is proposed to implement real time management of content caching,recommendation and delivery,which can approach the optimal solution without iterations during each decision epoch.Finally,the simulation results are provided to evaluate the performance of our proposed scheme,which show that it can achieve lower cost than the existing content caching and recommendation schemes.
文摘In software development projects,bugs are common phenomena.Developers report bugs in open source repositories.There is a need to develop high quality developer prediction model that considers developer work satisfaction,keep within limited development cost,and improve bug resolution time.To address and resolve bug report as soon as possible is the main focus of triager when a new bug is reported.Thus,developer work efficiency is an important factor in bug-fixing.To address these issues,a proposed approach recommends a set of developers that could potentially share their knowledge with each other to fix new bug reports.The proposed approach is called developer working efficiency and social network based developer recommendation(DweSn).It is a composite model that builds developers'profile by using developer average bug fixing time,work efficiency to fix variety of bugs,as well as the developer's social interactions with other developers.A similarity measure is applied between new bug and bugs in corpus to extract the list of capable developers from the corpus.The proposed approach only selects those developers who are active and less loaded with work.The developer with the highest profile score is assigned the bugs.We evaluated our approach on the subset of five large open-source projects including Mozilla,Netbeans,Eclipse,Firefox and OpenOffice,and compared it with the state-of-the-art.The results demonstrate that combination of developers'efficiency with their average bug fixing time and interactions in their social network gives good accuracy and efficiently reduces bug tossing length.This approach shows an improvement in prediction accuracy,precision,recall,F-score and reduced bug tossing length up to 93.89%,93.12%,93.46%,93.27%and 93.25%,respectively.The proposed approach achieved a 93%hit ratio and 93.34%mean reciprocal rank,indicating that our proposed triager is able to efficiently assign bugs to correct developers.
基金supported by the National Natural Science Foundation of China under Grant 61762031the Science and Technology Major Project of Guangxi Province under Grant AA19046004+2 种基金the Natural Science Foundation of Guangxi under Grant 2021JJA170130the Innovation Project of Guangxi Graduate Education under Grant YCSW2022326the Research Project of Guangxi Philosophy and Social Science Planning under Grant 21FGL040。
文摘The recommendation system(RS)on the strength of Graph Neural Networks(GNN)perceives a user-item interaction graph after collecting all items the user has interacted with.Afterward the RS performs neighborhood aggregation on the graph to generate long-term preference representations for the user in quick succession.However,user preferences are dynamic.With the passage of time and some trend guidance,users may generate some short-term preferences,which are more likely to lead to user-item interactions.A GNN recommendation based on long-and short-term preference(LSGNN)is proposed to address the above problems.LSGNN consists of four modules,using a GNN combined with the attention mechanism to extract long-term preference features,using Bidirectional Encoder Representation from Transformers(BERT)and the attention mechanism combined with Bi-Directional Gated Recurrent Unit(Bi-GRU)to extract short-term preference features,using Convolutional Neural Network(CNN)combined with the attention mechanism to add title and description representations of items,finally inner-producing long-term and short-term preference features as well as features of items to achieve recommendations.In experiments conducted on five publicly available datasets from Amazon,LSGNN is superior to state-of-the-art personalized recommendation techniques.
