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
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
Session-based recommendation predicts the user’s next action by exploring the item dependencies in an anonymous session.Most of the existing methods are based on the assumption that each session has a single intentio...Session-based recommendation predicts the user’s next action by exploring the item dependencies in an anonymous session.Most of the existing methods are based on the assumption that each session has a single intention,items irrelevant to the single intention will be regarded as noises.However,in real-life scenarios,sessions often contain multiple intentions.This paper designs a multi-channel Intention-aware Recurrent Unit(TARU)network to further mining these noises.The multi-channel TARU explicitly group items into the different channels by filtering items irrelevant to the current intention with the intention control unit.Furthermore,we propose to use the attention mechanism to adaptively generate an effective representation of the session’s final preference for the recommendation.The experimental results on two real-world datasets denote that our method performs well in session recommendation tasks and achieves improvement against several baselines on the general metrics.展开更多
Session-based recommendation aims to predict user preferences based on anonymous behavior sequences.Recent research on session-based recommendation systems has mainly focused on utilizing attention mechanisms on seque...Session-based recommendation aims to predict user preferences based on anonymous behavior sequences.Recent research on session-based recommendation systems has mainly focused on utilizing attention mechanisms on sequential patterns,which has achieved significant results.However,most existing studies only consider individual items in a session and do not extract information from continuous items,which can easily lead to the loss of information on item transition relationships.Therefore,this paper proposes a session-based recommendation algorithm(SGT)based on Gated Recurrent Unit(GRU)and Transformer,which captures user interests by learning continuous items in the current session and utilizes all item transitions on sessions in a more refined way.By combining short-term sessions and long-term behavior,user dynamic preferences are captured.Extensive experiments were conducted on three session-based recommendation datasets,and compared to the baseline methods,both the recall rate Recall@20 and the mean reciprocal rank MRR@20 of the SGT algorithm were improved,demonstrating the effectiveness of the SGT method.展开更多
Popularity plays a significant role in the recommendation system. Traditional popularity is only defined as a static ratio or metric (e.g., a ratio of users who have rated the item and the box office of a movie) regar...Popularity plays a significant role in the recommendation system. Traditional popularity is only defined as a static ratio or metric (e.g., a ratio of users who have rated the item and the box office of a movie) regardless of the previous trends of this ratio or metric and the attribute diversity of items. To solve this problem and reach accurate popularity, we creatively propose to extract the popularity of an item according to the Proportional Integral Differential (PID) idea. Specifically, Integral (I) integrates a physical quantity over a time window, which agrees with the fact that determining the attributes of items also requires a long-term observation. The Differential (D) emphasizes an incremental change of a physical quantity over time, which coincidentally caters to a trend. Moreover, in the Session-Based Recommendation (SBR) community, many methods extract session interests without considering the impact of popularity on interest, leading to suboptimal recommendation results. To further improve recommendation performance, we propose a novel strategy that leverages popularity to enhance the session interest (popularity-aware interest). The proposed popularity by PID is further used to construct the popularity-aware interest, which consistently improves the recommendation performance of the main models in the SBR community. For STAMP, SRGNN, GCSAN, and TAGNN, on Yoochoose1/64, the metric P@20 is relatively improved by 0.93%, 1.84%, 2.02%, and 2.53%, respectively, and MRR@20 is relatively improved by 3.74%, 1.23%, 2.72%, and 3.48%, respectively. On Movieslen-1m, the relative improvements of P@20 are 7.41%, 15.52%, 8.20%, and 20.12%, respectively, and that of MRR@20 are 2.34%, 12.41%, 20.34%, and 19.21%, respectively.展开更多
Session-based recommendation(SBR)and multibehavior recommendation(MBR)are both important problems and have attracted the attention of many researchers and practitioners.Different from SBR that solely uses one single t...Session-based recommendation(SBR)and multibehavior recommendation(MBR)are both important problems and have attracted the attention of many researchers and practitioners.Different from SBR that solely uses one single type of behavior sequences and MBR that neglects sequential dynamics,heterogeneous SBR(HSBR)that exploits different types of behavioral information(e.g.,examinations like clicks or browses,purchases,adds-to-carts and adds-to-favorites)in sequences is more consistent with real-world recommendation scenarios,but it is rarely studied.Early efforts towards HSBR focus on distinguishing different types of behaviors or exploiting homogeneous behavior transitions in a sequence with the same type of behaviors.However,all the existing solutions for HSBR do not exploit the rich heterogeneous behavior transitions in an explicit way and thus may fail to capture the semantic relations between different types of behaviors.However,all the existing solutions for HSBR do not model the rich heterogeneous behavior transitions in the form of graphs and thus may fail to capture the semantic relations between different types of behaviors.The limitation hinders the development of HSBR and results in unsatisfactory performance.As a response,we propose a novel behavior-aware graph neural network(BGNN)for HSBR.Our BGNN adopts a dual-channel learning strategy for differentiated modeling of two different types of behavior sequences in a session.Moreover,our BGNN integrates the information of both homogeneous behavior transitions and heterogeneous behavior transitions in a unified way.We then conduct extensive empirical studies on three real-world datasets,and find that our BGNN outperforms the best baseline by 21.87%,18.49%,and 37.16%on average correspondingly.A series of further experiments and visualization studies demonstrate the rationality and effectiveness of our BGNN.An exploratory study on extending our BGNN to handle more than two types of behaviors show that our BGNN can easily and effectively be extended to multibehavior scenarios.展开更多
Session-based recommendation is a popular research topic that aims to predict users’next possible interactive item by exploiting anonymous sessions.The existing studies mainly focus on making predictions by consideri...Session-based recommendation is a popular research topic that aims to predict users’next possible interactive item by exploiting anonymous sessions.The existing studies mainly focus on making predictions by considering users’single interactive behavior.Some recent efforts have been made to exploit multiple interactive behaviors,but they generally ignore the influences of different interactive behaviors and the noise in interactive sequences.To address these problems,we propose a behavior-aware graph neural network for session-based recommendation.First,different interactive sequences are modeled as directed graphs.Thus,the item representations are learned via graph neural networks.Then,a sparse self-attention module is designed to remove the noise in behavior sequences.Finally,the representations of different behavior sequences are aggregated with the gating mechanism to obtain the session representations.Experimental results on two public datasets show that our proposed method outperforms all competitive baselines.The source code is available at the website of GitHub.展开更多
Session-based recommendation aims to predict the next item based on a user’s limited interactions within a short period.Existing approaches use mainly recurrent neural networks(RNNs)or graph neural networks(GNNs)to m...Session-based recommendation aims to predict the next item based on a user’s limited interactions within a short period.Existing approaches use mainly recurrent neural networks(RNNs)or graph neural networks(GNNs)to model the sequential patterns or the transition relationships between items.However,such models either ignore the over-smoothing issue of GNNs,or directly use cross-entropy loss with a softmax layer for model optimization,which easily results in the over-fitting problem.To tackle the above issues,we propose a self-supervised graph learning with target-adaptive masking(SGL-TM)method.Specifically,we first construct a global graph based on all involved sessions and subsequently capture the self-supervised signals from the global connections between items,which helps supervise the model in generating accurate representations of items in the ongoing session.After that,we calculate the main supervised loss by comparing the ground truth with the predicted scores of items adjusted by our designed target-adaptive masking module.Finally,we combine the main supervised component with the auxiliary self-supervision module to obtain the final loss for optimizing the model parameters.Extensive experimental results from two benchmark datasets,Gowalla and Diginetica,indicate that SGL-TM can outperform state-of-the-art baselines in terms of Recall@20 and MRR@20,especially in short sessions.展开更多
Session-based recommender systems are increasingly applied to next-item recommendations.However,existing approaches encode the session information of each user independently and do not consider the interrelationship b...Session-based recommender systems are increasingly applied to next-item recommendations.However,existing approaches encode the session information of each user independently and do not consider the interrelationship between users.This work is based on the intuition that dynamic groups of like-minded users exist over time.By considering the impact of latent user groups,we can learn a user’s preference in a better way.To this end,we propose a recommendation model based on learning user embeddings by modeling long and short-term dynamic latent user groups.Specifically,we utilize two network units to learn users’long and short-term sessions,respectively.Meanwhile,we employ two additional units to determine the affiliation of users with specific latent groups,followed by an aggregation of these latent group representations.Finally,user preference representations are shaped comprehensively by considering all these four aspects,based on an attention mechanism.Moreover,to avoid setting the number of groups manually,we further incorporate an adaptive learning unit to assess the necessity for creating a new group and learn the representation of emerging groups automatically.Extensive experiments prove our model outperforms multiple state-of-the-art methods in terms of Recall,mean average precision(mAP),and area under curve(AUC)metrics.展开更多
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.
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This work is supported by Katie Shu Sui Pui Charitable Trust-Academic Publication Fellowship(Project Reference No.KSPF 2020-01)。
文摘Session-based recommendation predicts the user’s next action by exploring the item dependencies in an anonymous session.Most of the existing methods are based on the assumption that each session has a single intention,items irrelevant to the single intention will be regarded as noises.However,in real-life scenarios,sessions often contain multiple intentions.This paper designs a multi-channel Intention-aware Recurrent Unit(TARU)network to further mining these noises.The multi-channel TARU explicitly group items into the different channels by filtering items irrelevant to the current intention with the intention control unit.Furthermore,we propose to use the attention mechanism to adaptively generate an effective representation of the session’s final preference for the recommendation.The experimental results on two real-world datasets denote that our method performs well in session recommendation tasks and achieves improvement against several baselines on the general metrics.
基金supported by the Scientific Research Basic Ability Enhancement Program for Young and Middle-aged Teachers of Guangxi Higher Education Institutions,“Research on Deep Learning-based Recommendation Model and its Application”(Project No.2019KY0867)Guangxi Innovation-driven Development Special Project(Science and Technology Major Special Project)+2 种基金“Key Technology of Human-Machine Intelligent Interactive Touch Terminal Manufacturing and Industrial Cluster Application”(Project No.Guike AA21077018)“Touch display integrated intelligent touch system and industrial cluster application”(Project No.:Guike AA21077018-2)National Natural Science Foundation of China(Project No.:42065004).
文摘Session-based recommendation aims to predict user preferences based on anonymous behavior sequences.Recent research on session-based recommendation systems has mainly focused on utilizing attention mechanisms on sequential patterns,which has achieved significant results.However,most existing studies only consider individual items in a session and do not extract information from continuous items,which can easily lead to the loss of information on item transition relationships.Therefore,this paper proposes a session-based recommendation algorithm(SGT)based on Gated Recurrent Unit(GRU)and Transformer,which captures user interests by learning continuous items in the current session and utilizes all item transitions on sessions in a more refined way.By combining short-term sessions and long-term behavior,user dynamic preferences are captured.Extensive experiments were conducted on three session-based recommendation datasets,and compared to the baseline methods,both the recall rate Recall@20 and the mean reciprocal rank MRR@20 of the SGT algorithm were improved,demonstrating the effectiveness of the SGT method.
基金supported by the National Natural Science Foundation of China(No.62276278)Guangdong Basic and Applied Basic Research Foundation(No.2022A1515110006).
文摘Popularity plays a significant role in the recommendation system. Traditional popularity is only defined as a static ratio or metric (e.g., a ratio of users who have rated the item and the box office of a movie) regardless of the previous trends of this ratio or metric and the attribute diversity of items. To solve this problem and reach accurate popularity, we creatively propose to extract the popularity of an item according to the Proportional Integral Differential (PID) idea. Specifically, Integral (I) integrates a physical quantity over a time window, which agrees with the fact that determining the attributes of items also requires a long-term observation. The Differential (D) emphasizes an incremental change of a physical quantity over time, which coincidentally caters to a trend. Moreover, in the Session-Based Recommendation (SBR) community, many methods extract session interests without considering the impact of popularity on interest, leading to suboptimal recommendation results. To further improve recommendation performance, we propose a novel strategy that leverages popularity to enhance the session interest (popularity-aware interest). The proposed popularity by PID is further used to construct the popularity-aware interest, which consistently improves the recommendation performance of the main models in the SBR community. For STAMP, SRGNN, GCSAN, and TAGNN, on Yoochoose1/64, the metric P@20 is relatively improved by 0.93%, 1.84%, 2.02%, and 2.53%, respectively, and MRR@20 is relatively improved by 3.74%, 1.23%, 2.72%, and 3.48%, respectively. On Movieslen-1m, the relative improvements of P@20 are 7.41%, 15.52%, 8.20%, and 20.12%, respectively, and that of MRR@20 are 2.34%, 12.41%, 20.34%, and 19.21%, respectively.
基金support of the National Natural Science Foundation of China(Grant Nos.62172283 and 61836005).
文摘Session-based recommendation(SBR)and multibehavior recommendation(MBR)are both important problems and have attracted the attention of many researchers and practitioners.Different from SBR that solely uses one single type of behavior sequences and MBR that neglects sequential dynamics,heterogeneous SBR(HSBR)that exploits different types of behavioral information(e.g.,examinations like clicks or browses,purchases,adds-to-carts and adds-to-favorites)in sequences is more consistent with real-world recommendation scenarios,but it is rarely studied.Early efforts towards HSBR focus on distinguishing different types of behaviors or exploiting homogeneous behavior transitions in a sequence with the same type of behaviors.However,all the existing solutions for HSBR do not exploit the rich heterogeneous behavior transitions in an explicit way and thus may fail to capture the semantic relations between different types of behaviors.However,all the existing solutions for HSBR do not model the rich heterogeneous behavior transitions in the form of graphs and thus may fail to capture the semantic relations between different types of behaviors.The limitation hinders the development of HSBR and results in unsatisfactory performance.As a response,we propose a novel behavior-aware graph neural network(BGNN)for HSBR.Our BGNN adopts a dual-channel learning strategy for differentiated modeling of two different types of behavior sequences in a session.Moreover,our BGNN integrates the information of both homogeneous behavior transitions and heterogeneous behavior transitions in a unified way.We then conduct extensive empirical studies on three real-world datasets,and find that our BGNN outperforms the best baseline by 21.87%,18.49%,and 37.16%on average correspondingly.A series of further experiments and visualization studies demonstrate the rationality and effectiveness of our BGNN.An exploratory study on extending our BGNN to handle more than two types of behaviors show that our BGNN can easily and effectively be extended to multibehavior scenarios.
基金supported by the National Natural Science Foundation of China(Grant Nos.62072288,61702306,61433012)the Taishan Scholar Program of Shandong Province,the Natural Science Foundation of Shandong Province(ZR2018BF013,ZR2022MF268)the Open Project from CAS Key Lab of Network Data Science and Technology(CASNDST202007).
文摘Session-based recommendation is a popular research topic that aims to predict users’next possible interactive item by exploiting anonymous sessions.The existing studies mainly focus on making predictions by considering users’single interactive behavior.Some recent efforts have been made to exploit multiple interactive behaviors,but they generally ignore the influences of different interactive behaviors and the noise in interactive sequences.To address these problems,we propose a behavior-aware graph neural network for session-based recommendation.First,different interactive sequences are modeled as directed graphs.Thus,the item representations are learned via graph neural networks.Then,a sparse self-attention module is designed to remove the noise in behavior sequences.Finally,the representations of different behavior sequences are aggregated with the gating mechanism to obtain the session representations.Experimental results on two public datasets show that our proposed method outperforms all competitive baselines.The source code is available at the website of GitHub.
文摘Session-based recommendation aims to predict the next item based on a user’s limited interactions within a short period.Existing approaches use mainly recurrent neural networks(RNNs)or graph neural networks(GNNs)to model the sequential patterns or the transition relationships between items.However,such models either ignore the over-smoothing issue of GNNs,or directly use cross-entropy loss with a softmax layer for model optimization,which easily results in the over-fitting problem.To tackle the above issues,we propose a self-supervised graph learning with target-adaptive masking(SGL-TM)method.Specifically,we first construct a global graph based on all involved sessions and subsequently capture the self-supervised signals from the global connections between items,which helps supervise the model in generating accurate representations of items in the ongoing session.After that,we calculate the main supervised loss by comparing the ground truth with the predicted scores of items adjusted by our designed target-adaptive masking module.Finally,we combine the main supervised component with the auxiliary self-supervision module to obtain the final loss for optimizing the model parameters.Extensive experimental results from two benchmark datasets,Gowalla and Diginetica,indicate that SGL-TM can outperform state-of-the-art baselines in terms of Recall@20 and MRR@20,especially in short sessions.
基金supported by the National Natural Science Foundation of China(No.62202282)Shanghai Youth Science and Technology Talents Sailing Program(No.22YF1413700).
文摘Session-based recommender systems are increasingly applied to next-item recommendations.However,existing approaches encode the session information of each user independently and do not consider the interrelationship between users.This work is based on the intuition that dynamic groups of like-minded users exist over time.By considering the impact of latent user groups,we can learn a user’s preference in a better way.To this end,we propose a recommendation model based on learning user embeddings by modeling long and short-term dynamic latent user groups.Specifically,we utilize two network units to learn users’long and short-term sessions,respectively.Meanwhile,we employ two additional units to determine the affiliation of users with specific latent groups,followed by an aggregation of these latent group representations.Finally,user preference representations are shaped comprehensively by considering all these four aspects,based on an attention mechanism.Moreover,to avoid setting the number of groups manually,we further incorporate an adaptive learning unit to assess the necessity for creating a new group and learn the representation of emerging groups automatically.Extensive experiments prove our model outperforms multiple state-of-the-art methods in terms of Recall,mean average precision(mAP),and area under curve(AUC)metrics.
