Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)t...Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.展开更多
The goal of zero-shot recognition is to classify classes it has never seen before, which needs to build a bridge between seen and unseen classes through semantic embedding space. Therefore, semantic embedding space le...The goal of zero-shot recognition is to classify classes it has never seen before, which needs to build a bridge between seen and unseen classes through semantic embedding space. Therefore, semantic embedding space learning plays an important role in zero-shot recognition. Among existing works, semantic embedding space is mainly taken by user-defined attribute vectors. However, the discriminative information included in the user-defined attribute vector is limited. In this paper, we propose to learn an extra latent attribute space automatically to produce a more generalized and discriminative semantic embedded space. To prevent the bias problem, both user-defined attribute vector and latent attribute space are optimized by adversarial learning with auto-encoders. We also propose to reconstruct semantic patterns produced by explanatory graphs, which can make semantic embedding space more sensitive to usefully semantic information and less sensitive to useless information. The proposed method is evaluated on the AwA2 and CUB dataset. These results show that our proposed method achieves superior performance.展开更多
Computational analysis can accurately detect drug-gene interactions(DGIs)cost-effectively.However,transductive learning models are the hotspot to reveal the promising performance for unknown DGIs(both drugs and genes ...Computational analysis can accurately detect drug-gene interactions(DGIs)cost-effectively.However,transductive learning models are the hotspot to reveal the promising performance for unknown DGIs(both drugs and genes are present in the training model),without special attention to the unseen DGIs(both drugs and genes are absent in the training model).In view of this,this study,for the first time,proposed an inductive learning-based model for the precise identification of unseen DGIs.In our study,by integrating disease nodes to avoid data sparsity,a multi-relational drug-disease-gene(DDG)graph was constructed to achieve effective fusion of data on DDG intro-relationships and inter-actions.Following the extraction of graph features by utilizing graph embedding algorithms,our next step was the retrieval of the attributes of individual gene and drug nodes.In this way,a hybrid feature characterization was represented by integrating graph features and node attributes.Machine learning(ML)models were built,enabling the fulfillment of transductive predictions of unknown DGIs.To realize inductive learning,this study generated an innovative idea of transforming known node vectors derived from the DDG graph into representations of unseen nodes using node similarities as weights,enabling inductive predictions for the unseen DGIs.Consequently,the final model was superior to existing models,with significant improvement in predicting both external unknown and unseen DGIs.The practical feasibility of our model was further confirmed through case study and molecular docking.In summary,this study establishes an efficient data-driven approach through the proposed modeling,suggesting its value as a promising tool for accelerating drug discovery and repurposing.展开更多
Fault sensing in wind turbine(WT)generator bearings is essential for ensuring reliability and holding down maintenance costs.Feeding raw sensor data to machine learning(ML)model often overlooks the enveloping interdep...Fault sensing in wind turbine(WT)generator bearings is essential for ensuring reliability and holding down maintenance costs.Feeding raw sensor data to machine learning(ML)model often overlooks the enveloping interdependencies between system elements.This study proposes a new hybrid method that combines the domain knowledge via knowledge graphs(KGs)and the traditional feature-based data.Incorporation of contextual relationships through construction of graph embedding methods,such as Node2Vec,can capture meaningful information,such as the relationships among key parameters(e.g.wind speed,rotor Revolutions Per Minute(RPM),and temperature)in the enriched feature representations.These node embeddings,when augmented with the original data,can be used to allow the model to learn and generalize better.As shown in results achieved on experimental data,the augmented ML model(with KG)is much better at predicting with the help of accuracy and error measure compared to traditional ML methods.Paired t-test analysis proves the statistical validity of this improvement.Moreover,graph-based feature importance increases the interpretability of the model and helps to uncover the structurally significant variables that are otherwise ignored by the common methods.The approach provides an excellent,knowledge-guided manner through which intelligent fault detection can be executed on WT systems.展开更多
In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector spaces.However,parameter efficiency becomes increasingly crucial when dealing with l...In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector spaces.However,parameter efficiency becomes increasingly crucial when dealing with large-scale knowledge graphs that contain vast numbers of entities and relations.In particular,resource-intensive embeddings often lead to increased computational costs,and may limit scalability and adaptability in practical environ-ments,such as in low-resource settings or real-world applications.This paper explores an approach to knowledge graph representation learning that leverages small,reserved entities and relation sets for parameter-efficient embedding.We introduce a hierarchical attention network designed to refine and maximize the representational quality of embeddings by selectively focusing on these reserved sets,thereby reducing model complexity.Empirical assessments validate that our model achieves high performance on the benchmark dataset with fewer parameters and smaller embedding dimensions.The ablation studies further highlight the impact and contribution of each component in the proposed hierarchical attention structure.展开更多
Traffic accident data analysis and reasoning are crucial for accident prevention and control.Constructing an accident knowledge graph from hybrid datasets of Chinese and English accidents is a valuable task.However,it...Traffic accident data analysis and reasoning are crucial for accident prevention and control.Constructing an accident knowledge graph from hybrid datasets of Chinese and English accidents is a valuable task.However,it is challenging due to the need to consider multiple perspectives and infer implicit relationships between actors and factors in complex traffic accidents.To address these challenges,this paper proposes an accident learning attention embeddings based multi-view accident knowledge graph for traffic accident reasoning named BrightAccidentGraph.First,this paper proposes a multi-source traffic accident dataset construction and preprocessing method for traffic accident judgement records published by the China Judgement Document Network and traffic accident records published by the UK’s Ministry of Transport.Then,traffic accident graph construction and portrait method is proposed,we demonstrate the efficiency of the proposed method by constructing several multi-view traffic accident portraits using a multi-source dataset.Furthermore,accident learning attention embeddings based multi-view accident knowledge graph construction and traffic accident reasoning method using deep learning are introduced.Experiments on two hybrid datasets verify the efficiency and merits of our method.展开更多
Accurate prediction of future events brings great benefits and reduces losses for society in many domains,such as civil unrest,pandemics,and crimes.Knowledge graph is a general language for describing and modeling com...Accurate prediction of future events brings great benefits and reduces losses for society in many domains,such as civil unrest,pandemics,and crimes.Knowledge graph is a general language for describing and modeling complex systems.Different types of events continually occur,which are often related to historical and concurrent events.In this paper,we formalize the future event prediction as a temporal knowledge graph reasoning problem.Most existing studies either conduct reasoning on static knowledge graphs or assume knowledges graphs of all timestamps are available during the training process.As a result,they cannot effectively reason over temporal knowledge graphs and predict events happening in the future.To address this problem,some recent works learn to infer future events based on historical eventbased temporal knowledge graphs.However,these methods do not comprehensively consider the latent patterns and influences behind historical events and concurrent events simultaneously.This paper proposes a new graph representation learning model,namely Recurrent Event Graph ATtention Network(RE-GAT),based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently.More specifically,our RE-GAT uses an attention-based historical events embedding module to encode past events,and employs an attention-based concurrent events embedding module to model the associations of events at the same timestamp.A translation-based decoder module and a learning objective are developed to optimize the embeddings of entities and relations.We evaluate our proposed method on four benchmark datasets.Extensive experimental results demonstrate the superiority of our RE-GAT model comparing to various base-lines,which proves that our method can more accurately predict what events are going to happen.展开更多
To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge gra...To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge graph completion(KGC).Related research work has shown the superiority of convolutional neural networks(CNNs)in extracting semantic features of triple embeddings.However,these researches use only one single-shaped filter and fail to extract semantic features of different granularity.To solve this problem,ConvKG exploits multi-shaped filters to co-convolute on the triple embeddings,joint learning semantic features of different granularity.Different shaped filters cover different sizes on the triple embeddings and capture pairwise interactions of different granularity among triple elements.Experimental results confirm the strength of joint learning,and compared with state-of-the-art CNN-based KGC models,ConvKG achieves the better mean rank(MR)and Hits@10 metrics on dataset WN18 RR,and the better MR on dataset FB15k-237.展开更多
Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source projects.The existing CPDP approaches...Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source projects.The existing CPDP approaches rely on static metrics or dynamic syntactic features,which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties,such as complex design patterns,relationships between multiple functions,and dependencies in different software projects,that are important for CPDP.This paper introduces a novel approach,a graph-based feature learning model for CPDP(GB-CPDP),that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs(CFGs)and data dependency graphs(DDGs).These graphs capture the structural and data dependencies within the source code.The proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long Short-Term Memory(LSTM)networks to learn predictive models.The process involves graph construction,feature learning through graph embedding and LSTM,and defect prediction.Experimental evaluation using nine open-source Java projects from the PROMISE dataset demonstrates that GB-CPDP outperforms state-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve(AUC).The results showcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction.展开更多
This paper discusses about the new approach of multiple object track-ing relative to background information.The concept of multiple object tracking through background learning is based upon the theory of relativity,th...This paper discusses about the new approach of multiple object track-ing relative to background information.The concept of multiple object tracking through background learning is based upon the theory of relativity,that involves a frame of reference in spatial domain to localize and/or track any object.Thefield of multiple object tracking has seen a lot of research,but researchers have considered the background as redundant.However,in object tracking,the back-ground plays a vital role and leads to definite improvement in the overall process of tracking.In the present work an algorithm is proposed for the multiple object tracking through background learning.The learning framework is based on graph embedding approach for localizing multiple objects.The graph utilizes the inher-ent capabilities of depth modelling that assist in prior to track occlusion avoidance among multiple objects.The proposed algorithm has been compared with the recent work available in literature on numerous performance evaluation measures.It is observed that our proposed algorithm gives better performance.展开更多
Real-world complex networks are inherently heterogeneous;they have different types of nodes,attributes,and relationships.In recent years,various methods have been proposed to automatically learn how to encode the stru...Real-world complex networks are inherently heterogeneous;they have different types of nodes,attributes,and relationships.In recent years,various methods have been proposed to automatically learn how to encode the structural and semantic information contained in heterogeneous information networks(HINs)into low-dimensional embeddings;this task is called heterogeneous network embedding(HNE).Efficient HNE techniques can benefit various HIN-based machine learning tasks such as node classification,recommender systems,and information retrieval.Here,we provide a comprehensive survey of key advancements in the area of HNE.First,we define an encoder-decoder-based HNE model taxonomy.Then,we systematically overview,compare,and summarize various state-of-the-art HNE models and analyze the advantages and disadvantages of various model categories to identify more potentially competitive HNE frameworks.We also summarize the application fields,benchmark datasets,open source tools,andperformance evaluation in theHNEarea.Finally,wediscuss open issues and suggest promising future directions.We anticipate that this survey will provide deep insights into research in the field of HNE.展开更多
Big Data and artificial intelligence are used to transform businesses.Social networking sites have given a new dimension to online data.Social media platforms help gather massive amounts of data to reach a wide variet...Big Data and artificial intelligence are used to transform businesses.Social networking sites have given a new dimension to online data.Social media platforms help gather massive amounts of data to reach a wide variety of customers using influence maximization technique for innovative ideas,products and services.This paper aims to develop a deep learning method that can identify the influential users in a network.This method combines the various aspects of a user into a single graph.In a social network,the most influential user is the most trusted user.These significant users are used for viral marketing as the seeds to influence other users in the network.The proposed method combines both topical and topological aspects of a user in the network using collaborativefiltering.The proposed method is DeepWalk based Influence Maximization(DWIM).The proposed method was able tofind k influential nodes with computable time using the algorithm.The experiments are performed to assess the proposed algorithm,and centrality measures are used to compare the results.The results reveal its performance that the proposed method canfind k influential nodes in computable time.DWIM can identify influential users,which helps viral marketing,outlier detection,and recommendations for different products and services.After applying the proposed methodology,the set of seed nodes gives maximum influence measured with respect to different centrality measures in an increased computable time.展开更多
The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph,which is amenable to be adopted in tra...The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph,which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations.Graph embedding methods build an important bridge between social network analysis and data analytics,as social networks naturally generate an unprecedented volume of graph data continuously.Publishing social network data not only brings benefit for public health,disaster response,commercial promotion,and many other applications,but also gives birth to threats that jeopardize each individual’s privacy and security.Unfortunately,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks.To be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding.In this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links,while persevering sufficient non-sensitive information,such as graph topology and node attributes in graph embedding.Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.展开更多
Recommendation has been widely used in business scenarios to provide users with personalized and accurate item lists by efficiently analyzing complex user-item interactions.However,existing recommendation methods have...Recommendation has been widely used in business scenarios to provide users with personalized and accurate item lists by efficiently analyzing complex user-item interactions.However,existing recommendation methods have significant shortcomings in capturing the dynamic preference changes of users and discovering their true potential intents.To address these problems,a novel framework named Intent-Aware Graph-Level Embedding Learning(IaGEL)is proposed for recommendation.In this framework,the potential user interest is explored by capturing the co-occurrence of items in different periods,and then user interest is further improved based on an adaptive aggregation algorithm,forming generic intents and specific intents.In addition,for better representing the intents,graph-level embedding learning is designed based on the mutual information comparison among positive intents and negative intents.Finally,an intent-based recommendation strategy is designed to further mine the dynamic changes in user preferences.Experiments on three public and industrial datasets demonstrate the effectiveness of the proposed IaGEL in the task of recommendation.展开更多
Federated learning has been widely employed in many applications to protect the data privacy of participating clients.Although the dataset is decentralized among training devices in federated learning,the model parame...Federated learning has been widely employed in many applications to protect the data privacy of participating clients.Although the dataset is decentralized among training devices in federated learning,the model parameters are usually stored in a centralized manner.Centralized federated learning is easy to implement;however,a centralized scheme causes a communication bottleneck at the central server,which may significantly slow down the training process.To improve training efficiency,we investigate the decentralized federated learning scheme.The decentralized scheme has become feasible with the rapid development of device-to-device communication techniques under 5G.Nevertheless,the convergence rate of learning models in the decentralized scheme depends on the network topology design.We propose optimizing the topology design to improve training efficiency for decentralized federated learning,which is a non-trivial problem,especially when considering data heterogeneity.In this paper,we first demonstrate the advantage of hypercube topology and present a hypercube graph construction method to reduce data heterogeneity by carefully selecting neighbors of each training device—a process that resembles classic graph embedding.In addition,we propose a heuristic method for generating torus graphs.Moreover,we have explored the communication patterns in hypercube topology and propose a sequential synchronization scheme to reduce communication cost during training.A batch synchronization scheme is presented to fine-tune the communication pattern for hypercube topology.Experiments on real-world datasets show that our proposed graph construction methods can accelerate the training process,and our sequential synchronization scheme can significantly reduce the overall communication traffic during training.展开更多
The design and high-throughput screening of materials using machine-learning assisted quantummechanical simulations typically requires the existence of a very large data set,often generated from simulations at a high ...The design and high-throughput screening of materials using machine-learning assisted quantummechanical simulations typically requires the existence of a very large data set,often generated from simulations at a high level of theory or fidelity.Asingle simulation at high fidelity can take on the order of days for a complex molecule.Thus,although machine learning surrogate simulations seem promising at first glance,generation of the training data can defeat the original purpose.For this reason,the use of machine learning to screen or design materials remains elusive for many important applications.In this paper we introduce a new multi-fidelity approach based on a dual graph embedding to extract features that are placed inside a nonlinear multi-step autoregressive model.Experiments on five benchmark problems,with 14 different quantities and 27 different levels of theory,demonstrate the generalizability and high accuracy of the approach.It typically requires a few 10s to a few 1000’s of high-fidelity training points,which is several orders of magnitude lower than direct ML methods,and can be up to two orders of magnitude lower than other multi-fidelity methods.Furthermore,we develop a new benchmark data set for 860 benzoquinone molecules with up to 14 atoms,containing energy,HOMO,LUMO and dipole moment values at four levels of theory,up to coupled cluster with singles and doubles.展开更多
文摘Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.
文摘The goal of zero-shot recognition is to classify classes it has never seen before, which needs to build a bridge between seen and unseen classes through semantic embedding space. Therefore, semantic embedding space learning plays an important role in zero-shot recognition. Among existing works, semantic embedding space is mainly taken by user-defined attribute vectors. However, the discriminative information included in the user-defined attribute vector is limited. In this paper, we propose to learn an extra latent attribute space automatically to produce a more generalized and discriminative semantic embedded space. To prevent the bias problem, both user-defined attribute vector and latent attribute space are optimized by adversarial learning with auto-encoders. We also propose to reconstruct semantic patterns produced by explanatory graphs, which can make semantic embedding space more sensitive to usefully semantic information and less sensitive to useless information. The proposed method is evaluated on the AwA2 and CUB dataset. These results show that our proposed method achieves superior performance.
基金funded by the National Natural Science Foundation of China(Grant No.:22173065)the Sichuan International Science and Technology Innovation Cooperation Project,China(Grant No.:24GJHZ0431).
文摘Computational analysis can accurately detect drug-gene interactions(DGIs)cost-effectively.However,transductive learning models are the hotspot to reveal the promising performance for unknown DGIs(both drugs and genes are present in the training model),without special attention to the unseen DGIs(both drugs and genes are absent in the training model).In view of this,this study,for the first time,proposed an inductive learning-based model for the precise identification of unseen DGIs.In our study,by integrating disease nodes to avoid data sparsity,a multi-relational drug-disease-gene(DDG)graph was constructed to achieve effective fusion of data on DDG intro-relationships and inter-actions.Following the extraction of graph features by utilizing graph embedding algorithms,our next step was the retrieval of the attributes of individual gene and drug nodes.In this way,a hybrid feature characterization was represented by integrating graph features and node attributes.Machine learning(ML)models were built,enabling the fulfillment of transductive predictions of unknown DGIs.To realize inductive learning,this study generated an innovative idea of transforming known node vectors derived from the DDG graph into representations of unseen nodes using node similarities as weights,enabling inductive predictions for the unseen DGIs.Consequently,the final model was superior to existing models,with significant improvement in predicting both external unknown and unseen DGIs.The practical feasibility of our model was further confirmed through case study and molecular docking.In summary,this study establishes an efficient data-driven approach through the proposed modeling,suggesting its value as a promising tool for accelerating drug discovery and repurposing.
文摘Fault sensing in wind turbine(WT)generator bearings is essential for ensuring reliability and holding down maintenance costs.Feeding raw sensor data to machine learning(ML)model often overlooks the enveloping interdependencies between system elements.This study proposes a new hybrid method that combines the domain knowledge via knowledge graphs(KGs)and the traditional feature-based data.Incorporation of contextual relationships through construction of graph embedding methods,such as Node2Vec,can capture meaningful information,such as the relationships among key parameters(e.g.wind speed,rotor Revolutions Per Minute(RPM),and temperature)in the enriched feature representations.These node embeddings,when augmented with the original data,can be used to allow the model to learn and generalize better.As shown in results achieved on experimental data,the augmented ML model(with KG)is much better at predicting with the help of accuracy and error measure compared to traditional ML methods.Paired t-test analysis proves the statistical validity of this improvement.Moreover,graph-based feature importance increases the interpretability of the model and helps to uncover the structurally significant variables that are otherwise ignored by the common methods.The approach provides an excellent,knowledge-guided manner through which intelligent fault detection can be executed on WT systems.
基金supported by the National Science and Technology Council(NSTC),Taiwan,under Grants Numbers 112-2622-E-029-009 and 112-2221-E-029-019.
文摘In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector spaces.However,parameter efficiency becomes increasingly crucial when dealing with large-scale knowledge graphs that contain vast numbers of entities and relations.In particular,resource-intensive embeddings often lead to increased computational costs,and may limit scalability and adaptability in practical environ-ments,such as in low-resource settings or real-world applications.This paper explores an approach to knowledge graph representation learning that leverages small,reserved entities and relation sets for parameter-efficient embedding.We introduce a hierarchical attention network designed to refine and maximize the representational quality of embeddings by selectively focusing on these reserved sets,thereby reducing model complexity.Empirical assessments validate that our model achieves high performance on the benchmark dataset with fewer parameters and smaller embedding dimensions.The ablation studies further highlight the impact and contribution of each component in the proposed hierarchical attention structure.
基金supported by the Key Project of College-bureau Cooperation of Beijing Police College(No.2022KXJ12)the Key Project of Ministry of Public Security Police Equipment R&D Program(No.2023ZB12)+3 种基金the National Key R&D Program of China(No.2022YFB2703500)the Opening Project of Key Laboratory of Evidence Science(China University of Political Science and Law),the Ministry of Education(No.2022KFKT09)the National Natural Science Foundation of China(No.62272026)the Beijing University of Aeronautics and Astronautics teaching and research projects“Research on teaching methods of research methods course driven by process-based practice ability training”and“Research on teaching methods of introduction to mobile computing driven by practice ability training”.
文摘Traffic accident data analysis and reasoning are crucial for accident prevention and control.Constructing an accident knowledge graph from hybrid datasets of Chinese and English accidents is a valuable task.However,it is challenging due to the need to consider multiple perspectives and infer implicit relationships between actors and factors in complex traffic accidents.To address these challenges,this paper proposes an accident learning attention embeddings based multi-view accident knowledge graph for traffic accident reasoning named BrightAccidentGraph.First,this paper proposes a multi-source traffic accident dataset construction and preprocessing method for traffic accident judgement records published by the China Judgement Document Network and traffic accident records published by the UK’s Ministry of Transport.Then,traffic accident graph construction and portrait method is proposed,we demonstrate the efficiency of the proposed method by constructing several multi-view traffic accident portraits using a multi-source dataset.Furthermore,accident learning attention embeddings based multi-view accident knowledge graph construction and traffic accident reasoning method using deep learning are introduced.Experiments on two hybrid datasets verify the efficiency and merits of our method.
基金supported by the National Natural Science Foundation of China under grants U19B2044National Key Research and Development Program of China(2021YFC3300500).
文摘Accurate prediction of future events brings great benefits and reduces losses for society in many domains,such as civil unrest,pandemics,and crimes.Knowledge graph is a general language for describing and modeling complex systems.Different types of events continually occur,which are often related to historical and concurrent events.In this paper,we formalize the future event prediction as a temporal knowledge graph reasoning problem.Most existing studies either conduct reasoning on static knowledge graphs or assume knowledges graphs of all timestamps are available during the training process.As a result,they cannot effectively reason over temporal knowledge graphs and predict events happening in the future.To address this problem,some recent works learn to infer future events based on historical eventbased temporal knowledge graphs.However,these methods do not comprehensively consider the latent patterns and influences behind historical events and concurrent events simultaneously.This paper proposes a new graph representation learning model,namely Recurrent Event Graph ATtention Network(RE-GAT),based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently.More specifically,our RE-GAT uses an attention-based historical events embedding module to encode past events,and employs an attention-based concurrent events embedding module to model the associations of events at the same timestamp.A translation-based decoder module and a learning objective are developed to optimize the embeddings of entities and relations.We evaluate our proposed method on four benchmark datasets.Extensive experimental results demonstrate the superiority of our RE-GAT model comparing to various base-lines,which proves that our method can more accurately predict what events are going to happen.
基金Supported by the National Natural Science Foundation of China(No.61876144)。
文摘To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge graph completion(KGC).Related research work has shown the superiority of convolutional neural networks(CNNs)in extracting semantic features of triple embeddings.However,these researches use only one single-shaped filter and fail to extract semantic features of different granularity.To solve this problem,ConvKG exploits multi-shaped filters to co-convolute on the triple embeddings,joint learning semantic features of different granularity.Different shaped filters cover different sizes on the triple embeddings and capture pairwise interactions of different granularity among triple elements.Experimental results confirm the strength of joint learning,and compared with state-of-the-art CNN-based KGC models,ConvKG achieves the better mean rank(MR)and Hits@10 metrics on dataset WN18 RR,and the better MR on dataset FB15k-237.
基金supported by Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2022-00155885).
文摘Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source projects.The existing CPDP approaches rely on static metrics or dynamic syntactic features,which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties,such as complex design patterns,relationships between multiple functions,and dependencies in different software projects,that are important for CPDP.This paper introduces a novel approach,a graph-based feature learning model for CPDP(GB-CPDP),that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs(CFGs)and data dependency graphs(DDGs).These graphs capture the structural and data dependencies within the source code.The proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long Short-Term Memory(LSTM)networks to learn predictive models.The process involves graph construction,feature learning through graph embedding and LSTM,and defect prediction.Experimental evaluation using nine open-source Java projects from the PROMISE dataset demonstrates that GB-CPDP outperforms state-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve(AUC).The results showcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction.
文摘This paper discusses about the new approach of multiple object track-ing relative to background information.The concept of multiple object tracking through background learning is based upon the theory of relativity,that involves a frame of reference in spatial domain to localize and/or track any object.Thefield of multiple object tracking has seen a lot of research,but researchers have considered the background as redundant.However,in object tracking,the back-ground plays a vital role and leads to definite improvement in the overall process of tracking.In the present work an algorithm is proposed for the multiple object tracking through background learning.The learning framework is based on graph embedding approach for localizing multiple objects.The graph utilizes the inher-ent capabilities of depth modelling that assist in prior to track occlusion avoidance among multiple objects.The proposed algorithm has been compared with the recent work available in literature on numerous performance evaluation measures.It is observed that our proposed algorithm gives better performance.
基金supported by the National Key Research and Development Plan of China(2017YFB0503700,2016YFB0501801)the National Natural Science Foundation of China(61170026,62173157)+1 种基金the Thirteen Five-Year Research Planning Project of National Language Committee(No.YB135-149)the Fundamental Research Funds for the Central Universities(Nos.CCNU20QN022,CCNU20QN021,CCNU20ZT012).
文摘Real-world complex networks are inherently heterogeneous;they have different types of nodes,attributes,and relationships.In recent years,various methods have been proposed to automatically learn how to encode the structural and semantic information contained in heterogeneous information networks(HINs)into low-dimensional embeddings;this task is called heterogeneous network embedding(HNE).Efficient HNE techniques can benefit various HIN-based machine learning tasks such as node classification,recommender systems,and information retrieval.Here,we provide a comprehensive survey of key advancements in the area of HNE.First,we define an encoder-decoder-based HNE model taxonomy.Then,we systematically overview,compare,and summarize various state-of-the-art HNE models and analyze the advantages and disadvantages of various model categories to identify more potentially competitive HNE frameworks.We also summarize the application fields,benchmark datasets,open source tools,andperformance evaluation in theHNEarea.Finally,wediscuss open issues and suggest promising future directions.We anticipate that this survey will provide deep insights into research in the field of HNE.
文摘Big Data and artificial intelligence are used to transform businesses.Social networking sites have given a new dimension to online data.Social media platforms help gather massive amounts of data to reach a wide variety of customers using influence maximization technique for innovative ideas,products and services.This paper aims to develop a deep learning method that can identify the influential users in a network.This method combines the various aspects of a user into a single graph.In a social network,the most influential user is the most trusted user.These significant users are used for viral marketing as the seeds to influence other users in the network.The proposed method combines both topical and topological aspects of a user in the network using collaborativefiltering.The proposed method is DeepWalk based Influence Maximization(DWIM).The proposed method was able tofind k influential nodes with computable time using the algorithm.The experiments are performed to assess the proposed algorithm,and centrality measures are used to compare the results.The results reveal its performance that the proposed method canfind k influential nodes in computable time.DWIM can identify influential users,which helps viral marketing,outlier detection,and recommendations for different products and services.After applying the proposed methodology,the set of seed nodes gives maximum influence measured with respect to different centrality measures in an increased computable time.
基金supported by the National Science Foundation of USA(Nos.1829674,1912753,1704287,and 2011845)。
文摘The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph,which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations.Graph embedding methods build an important bridge between social network analysis and data analytics,as social networks naturally generate an unprecedented volume of graph data continuously.Publishing social network data not only brings benefit for public health,disaster response,commercial promotion,and many other applications,but also gives birth to threats that jeopardize each individual’s privacy and security.Unfortunately,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks.To be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding.In this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links,while persevering sufficient non-sensitive information,such as graph topology and node attributes in graph embedding.Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.
基金supported by the Zhejiang Provincial Natural Science Foundation of China under Grant No.LR21F020002the National Natural Science Foundation of China under Grant No.61976192.
文摘Recommendation has been widely used in business scenarios to provide users with personalized and accurate item lists by efficiently analyzing complex user-item interactions.However,existing recommendation methods have significant shortcomings in capturing the dynamic preference changes of users and discovering their true potential intents.To address these problems,a novel framework named Intent-Aware Graph-Level Embedding Learning(IaGEL)is proposed for recommendation.In this framework,the potential user interest is explored by capturing the co-occurrence of items in different periods,and then user interest is further improved based on an adaptive aggregation algorithm,forming generic intents and specific intents.In addition,for better representing the intents,graph-level embedding learning is designed based on the mutual information comparison among positive intents and negative intents.Finally,an intent-based recommendation strategy is designed to further mine the dynamic changes in user preferences.Experiments on three public and industrial datasets demonstrate the effectiveness of the proposed IaGEL in the task of recommendation.
基金This work was supported in part by the National Science Foundation(NSF)(Nos.SaTC 2310298,CNS 2214940,CPS 2128378,CNS 2107014,CNS 2150152,CNS 1824440,CNS 1828363,and CNS 1757533).
文摘Federated learning has been widely employed in many applications to protect the data privacy of participating clients.Although the dataset is decentralized among training devices in federated learning,the model parameters are usually stored in a centralized manner.Centralized federated learning is easy to implement;however,a centralized scheme causes a communication bottleneck at the central server,which may significantly slow down the training process.To improve training efficiency,we investigate the decentralized federated learning scheme.The decentralized scheme has become feasible with the rapid development of device-to-device communication techniques under 5G.Nevertheless,the convergence rate of learning models in the decentralized scheme depends on the network topology design.We propose optimizing the topology design to improve training efficiency for decentralized federated learning,which is a non-trivial problem,especially when considering data heterogeneity.In this paper,we first demonstrate the advantage of hypercube topology and present a hypercube graph construction method to reduce data heterogeneity by carefully selecting neighbors of each training device—a process that resembles classic graph embedding.In addition,we propose a heuristic method for generating torus graphs.Moreover,we have explored the communication patterns in hypercube topology and propose a sequential synchronization scheme to reduce communication cost during training.A batch synchronization scheme is presented to fine-tune the communication pattern for hypercube topology.Experiments on real-world datasets show that our proposed graph construction methods can accelerate the training process,and our sequential synchronization scheme can significantly reduce the overall communication traffic during training.
文摘The design and high-throughput screening of materials using machine-learning assisted quantummechanical simulations typically requires the existence of a very large data set,often generated from simulations at a high level of theory or fidelity.Asingle simulation at high fidelity can take on the order of days for a complex molecule.Thus,although machine learning surrogate simulations seem promising at first glance,generation of the training data can defeat the original purpose.For this reason,the use of machine learning to screen or design materials remains elusive for many important applications.In this paper we introduce a new multi-fidelity approach based on a dual graph embedding to extract features that are placed inside a nonlinear multi-step autoregressive model.Experiments on five benchmark problems,with 14 different quantities and 27 different levels of theory,demonstrate the generalizability and high accuracy of the approach.It typically requires a few 10s to a few 1000’s of high-fidelity training points,which is several orders of magnitude lower than direct ML methods,and can be up to two orders of magnitude lower than other multi-fidelity methods.Furthermore,we develop a new benchmark data set for 860 benzoquinone molecules with up to 14 atoms,containing energy,HOMO,LUMO and dipole moment values at four levels of theory,up to coupled cluster with singles and doubles.
