Pub Date : 2024-12-02DOI: 10.1109/TKDE.2024.3509912
Guoli Wu;Zhiyong Feng;Shizhan Chen;Hongyue Wu;Xiao Xue;Jianmao Xiao;Guodong Fan;Hongqi Chen;Jingyu Li
Traditional recommendation systems focus on maximizing user satisfaction by suggesting their favorite items. This user-centric approach may lead to unfair exposure distribution among the providers. On the contrary, a provider-centric design might become unfair to the users. Therefore, this paper proposes a re-ranking model FairSort 1 to find a trade-off solution among user-side fairness, provider-side fairness, and personalized recommendations utility. Previous works habitually treat this issue as a knapsack problem, incorporating both-side fairness as constraints. In this paper, we adopt a novel perspective, treating each recommendation list as a runway rather than a knapsack. In this perspective, each item on the runway gains a velocity and runs within a specific time, achieving re-ranking for both-side fairness. Meanwhile, we ensure the Minimum Utility Guarantee for personalized recommendations by designing a Binary Search approach. This can provide more reliable recommendations compared to the conventional greedy strategy based on the knapsack problem. We further broaden the applicability of FairSort, designing two versions for online and offline recommendation scenarios. Theoretical analysis and extensive experiments on real-world datasets indicate that FairSort can ensure more reliable personalized recommendations while considering fairness for both the provider and user.
{"title":"FairSort: Learning to Fair Rank for Personalized Recommendations in Two-Sided Platforms","authors":"Guoli Wu;Zhiyong Feng;Shizhan Chen;Hongyue Wu;Xiao Xue;Jianmao Xiao;Guodong Fan;Hongqi Chen;Jingyu Li","doi":"10.1109/TKDE.2024.3509912","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3509912","url":null,"abstract":"Traditional recommendation systems focus on maximizing user satisfaction by suggesting their favorite items. This user-centric approach may lead to unfair exposure distribution among the providers. On the contrary, a provider-centric design might become unfair to the users. Therefore, this paper proposes a re-ranking model FairSort\u0000<sup>1</sup>\u0000 to find a trade-off solution among user-side fairness, provider-side fairness, and personalized recommendations utility. Previous works habitually treat this issue as a knapsack problem, incorporating both-side fairness as constraints. In this paper, we adopt a novel perspective, treating each recommendation list as a runway rather than a knapsack. In this perspective, each item on the runway gains a velocity and runs within a specific time, achieving re-ranking for both-side fairness. Meanwhile, we ensure the Minimum Utility Guarantee for personalized recommendations by designing a Binary Search approach. This can provide more reliable recommendations compared to the conventional greedy strategy based on the knapsack problem. We further broaden the applicability of FairSort, designing two versions for online and offline recommendation scenarios. Theoretical analysis and extensive experiments on real-world datasets indicate that FairSort can ensure more reliable personalized recommendations while considering fairness for both the provider and user.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"641-654"},"PeriodicalIF":8.9,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Modern machine learning (ML) models have grown to a scale where training them on a single machine becomes impractical. As a result, there is a growing trend to leverage federated learning (FL) techniques to train large ML models in a distributed and collaborative manner. These models, however, when deployed on new devices, might struggle to generalize well due to domain shifts. In this context, federated domain adaptation (FDA) emerges as a powerful approach to address this challenge. Most existing FDA approaches typically focus on aligning the distributions between source and target domains by minimizing their (e.g., MMD) distance. Such strategies, however, inevitably introduce high communication overheads and can be highly sensitive to network reliability. In this paper, we introduce RF-TCA, an enhancement to the standard Transfer Component Analysis approach that significantly accelerates computation without compromising theoretical and empirical performance. Leveraging the computational advantage of RF-TCA, we further extend it to FDA setting with FedRF-TCA. The proposed FedRF-TCA protocol boasts communication complexity that is independent of the sample size, while maintaining performance that is either comparable to or even surpasses state-of-the-art FDA methods. We present extensive experiments to showcase the superior performance and robustness (to network condition) of FedRF-TCA.
{"title":"Robust and Communication-Efficient Federated Domain Adaptation via Random Features","authors":"Zhanbo Feng;Yuanjie Wang;Jie Li;Fan Yang;Jiong Lou;Tiebin Mi;Robert Caiming Qiu;Zhenyu Liao","doi":"10.1109/TKDE.2024.3510296","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3510296","url":null,"abstract":"Modern machine learning (ML) models have grown to a scale where training them on a single machine becomes impractical. As a result, there is a growing trend to leverage federated learning (FL) techniques to train large ML models in a distributed and collaborative manner. These models, however, when deployed on new devices, might struggle to generalize well due to domain shifts. In this context, federated domain adaptation (FDA) emerges as a powerful approach to address this challenge. Most existing FDA approaches typically focus on aligning the distributions between source and target domains by minimizing their (e.g., MMD) distance. Such strategies, however, inevitably introduce high communication overheads and can be highly sensitive to network reliability. In this paper, we introduce RF-TCA, an enhancement to the standard Transfer Component Analysis approach that significantly accelerates computation without compromising theoretical and empirical performance. Leveraging the computational advantage of RF-TCA, we further extend it to FDA setting with FedRF-TCA. The proposed FedRF-TCA protocol boasts communication complexity that is <italic>independent</i> of the sample size, while maintaining performance that is either comparable to or even surpasses state-of-the-art FDA methods. We present extensive experiments to showcase the superior performance and robustness (to network condition) of FedRF-TCA.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1411-1424"},"PeriodicalIF":8.9,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-02DOI: 10.1109/TKDE.2024.3508256
Wei Wu;Shiqi Li;Mi Jiang;Chuan Luo;Fangfang Li
Attributed network embedding seeks to depict each network node via a compact, low-dimensional vector while effectively preserving the similarity between node pairs, which lays a strong foundation for a great many high-level network mining tasks. With the advent of the era of Big Data, the number of nodes and edges has reached billions in many real-world networks, which poses great computational and storage challenges to the existing methods. Although some algorithms have been developed to handle billion-scale networks, they often undergo accuracy degradation or tempo-spatial inefficiency owing to attribute information loss or substantial parameter learning. To this end, we propose a simple, time- and space-efficient billion-scale attributed network embedding algorithm called SketchBANE in this paper, which strikes an excellent balance between accuracy and efficiency by adopting sparse random projection with 1-bit quantization to sketch the iterative closed neighborhood and maintain the similarity among high-order nodes in a non-learning manner. The extensive experimental results indicate that our proposed SketchBANE algorithm competes favorably with the state-of-the-art approaches, while remarkably reducing runtime and space consumption. Also, the proposed SketchBANE algorithm exhibits good scalability and parallelization.
{"title":"Time- and Space-Efficiently Sketching Billion-Scale Attributed Networks","authors":"Wei Wu;Shiqi Li;Mi Jiang;Chuan Luo;Fangfang Li","doi":"10.1109/TKDE.2024.3508256","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3508256","url":null,"abstract":"Attributed network embedding seeks to depict each network node via a compact, low-dimensional vector while effectively preserving the similarity between node pairs, which lays a strong foundation for a great many high-level network mining tasks. With the advent of the era of Big Data, the number of nodes and edges has reached billions in many real-world networks, which poses great computational and storage challenges to the existing methods. Although some algorithms have been developed to handle billion-scale networks, they often undergo accuracy degradation or tempo-spatial inefficiency owing to attribute information loss or substantial parameter learning. To this end, we propose a simple, time- and space-efficient billion-scale attributed network embedding algorithm called SketchBANE in this paper, which strikes an excellent balance between accuracy and efficiency by adopting sparse random projection with 1-bit quantization to sketch the iterative closed neighborhood and maintain the similarity among high-order nodes in a non-learning manner. The extensive experimental results indicate that our proposed SketchBANE algorithm competes favorably with the state-of-the-art approaches, while remarkably reducing runtime and space consumption. Also, the proposed SketchBANE algorithm exhibits good scalability and parallelization.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"966-978"},"PeriodicalIF":8.9,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-29DOI: 10.1109/TKDE.2024.3509416
Zeyu Zhang;Chaozhuo Li;Xu Chen;Xing Xie;Philip S. Yu
Meta learning has been recognized as an effective remedy for solving the cold-start problem in the recommendation domain. Existing models aim to learn how to generalize from the user behaviors in the training set to testing set. However, in the cold start settings, with only a small number of training samples, the testing distribution may easily deviate from the training one, which may invalidate the learned generalization patterns, and lower the recommendation performance. For alleviating this problem, in this paper, we propose a robust meta recommender framework to address the distribution shift problem. In specific, we argue that the distribution shift may exist on both the user- and interaction-levels, and in order to mitigate them simultaneously, we design a novel distributionally robust model by hierarchically reweighing the training samples. Different sample weights correspond to different training distributions, and we minimize the largest loss induced by the sample weights in a simplex, which essentially optimizes the upper bound of the testing loss. In addition, we analyze our framework on the convergence rates and generalization error bound to provide more theoretical insights. Empirically, we conduct extensive experiments based on different meta recommender models and real-world datasets to verify the generality and effectiveness of our framework.
{"title":"Meta Recommendation With Robustness Improvement","authors":"Zeyu Zhang;Chaozhuo Li;Xu Chen;Xing Xie;Philip S. Yu","doi":"10.1109/TKDE.2024.3509416","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3509416","url":null,"abstract":"Meta learning has been recognized as an effective remedy for solving the cold-start problem in the recommendation domain. Existing models aim to learn how to generalize from the user behaviors in the training set to testing set. However, in the cold start settings, with only a small number of training samples, the testing distribution may easily deviate from the training one, which may invalidate the learned generalization patterns, and lower the recommendation performance. For alleviating this problem, in this paper, we propose a robust meta recommender framework to address the distribution shift problem. In specific, we argue that the distribution shift may exist on both the user- and interaction-levels, and in order to mitigate them simultaneously, we design a novel distributionally robust model by hierarchically reweighing the training samples. Different sample weights correspond to different training distributions, and we minimize the largest loss induced by the sample weights in a simplex, which essentially optimizes the upper bound of the testing loss. In addition, we analyze our framework on the convergence rates and generalization error bound to provide more theoretical insights. Empirically, we conduct extensive experiments based on different meta recommender models and real-world datasets to verify the generality and effectiveness of our framework.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"781-793"},"PeriodicalIF":8.9,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-29DOI: 10.1109/TKDE.2024.3509454
Jie Li;Ke Deng;Jianxin Li;Yongli Ren
Session-based Recommender Systems (SBRSs) aim at timely predicting the next likely item by capturing users’ current preferences in sessions. Existing SBRSs research only focuses on maximizing session utilities, and little has been done on the fairness issue in SBRSs, which is vital but different from the same issue in traditional Recommender Systems (RSs). To fill in this gap, we define a novel concept of session-oriented fairness to enforce individual items to have the same exposure accumulated within each single session, which is flexible enough to provide opportunities to achieve different fairness goals. Then, we devise a Session-Oriented Fairness-Aware algorithm ( SOFA ) with a dual Temporal Convolutional Networks (TCN) architecture: one is SOUP (Session-Oriented Utility Promoter) and the other is SODA (Session-Oriented Disparity Alleviator). Benefit from the collaborative learning of SOUP and SODA for the evolution of accumulated exposure in sessions, SOFA is effective to maximize session-oriented fairness while maintaining high session utilities. To the best of our knowledge, this research is the first to solve fairness issues in SBRSs. Extensive experiments on real-world datasets demonstrate that SOFA outperforms the state-of-the-art approaches in terms of both utility and fairness.
{"title":"Session-Oriented Fairness-Aware Recommendation via Dual Temporal Convolutional Networks","authors":"Jie Li;Ke Deng;Jianxin Li;Yongli Ren","doi":"10.1109/TKDE.2024.3509454","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3509454","url":null,"abstract":"Session-based Recommender Systems (SBRSs) aim at timely predicting the next likely item by capturing users’ current preferences in sessions. Existing SBRSs research only focuses on maximizing session utilities, and little has been done on the fairness issue in SBRSs, which is vital but different from the same issue in traditional Recommender Systems (RSs). To fill in this gap, we define a novel concept of \u0000<italic>session-oriented fairness</i>\u0000 to enforce individual items to have the same exposure accumulated within each single session, which is flexible enough to provide opportunities to achieve different fairness goals. Then, we devise a Session-Oriented Fairness-Aware algorithm (\u0000<italic>SOFA</i>\u0000) with a dual Temporal Convolutional Networks (TCN) architecture: one is SOUP (Session-Oriented Utility Promoter) and the other is SODA (Session-Oriented Disparity Alleviator). Benefit from the collaborative learning of SOUP and SODA for the evolution of accumulated exposure in sessions, \u0000<italic>SOFA</i>\u0000 is effective to maximize session-oriented fairness while maintaining high session utilities. To the best of our knowledge, this research is the first to solve fairness issues in SBRSs. Extensive experiments on real-world datasets demonstrate that \u0000<italic>SOFA</i>\u0000 outperforms the state-of-the-art approaches in terms of both utility and fairness.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"923-935"},"PeriodicalIF":8.9,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-29DOI: 10.1109/TKDE.2024.3509024
Zhihui Wang;Jianrui Chen;Zhongshi Shao;Zhen Wang
Hyperedges, as extensions of pairwise edges, can characterize higher-order relations among multiple individuals. Due to the necessity of hypergraph detection in practical systems, hyperedge prediction has become a frontier problem in complex networks. However, previous hyperedge prediction models encounter three challenges: (i) failing to predict dynamic and arbitrary-order hyperedges simultaneously, (ii) confusing higher-order and lower-order features together to propagate neighborhood information, and (iii) lacking the capability to learn physical evolution laws, which lead to poor performance of the models. To tackle these challenges, we propose D $^{3}$ HP, a D ual-view D esynchronization hypergraph learning for arbitrary-order D ynamic H yperedge P rediction. Specifically, D $^{3}$ HP extracts the dynamic higher-order and lower-order features of hyperedges separately through an elastic hypergraph neural network (EHGNN) and an alternate desynchronization graph convolutional network (ADGCN) at each time snapshot. EHGNN is designed to incrementally mine the implicit higher-order relations and propagate neighborhood information. Moreover, ADGCN aims to combine GCN with desynchronization learining to learn the physical evolution of lower-order relations and alleviate the over-smoothing problem. Further, we improve the prediction performance of the model by rationally fusing the features learned from the dual views. Extensive experiments on 8 dynamic higher-order networks demonstrate that D $^{3}$ HP outperforms 14 state-of-the-art baselines.
{"title":"Dual-View Desynchronization Hypergraph Learning for Dynamic Hyperedge Prediction","authors":"Zhihui Wang;Jianrui Chen;Zhongshi Shao;Zhen Wang","doi":"10.1109/TKDE.2024.3509024","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3509024","url":null,"abstract":"Hyperedges, as extensions of pairwise edges, can characterize higher-order relations among multiple individuals. Due to the necessity of hypergraph detection in practical systems, hyperedge prediction has become a frontier problem in complex networks. However, previous hyperedge prediction models encounter three challenges: (i) failing to predict dynamic and arbitrary-order hyperedges simultaneously, (ii) confusing higher-order and lower-order features together to propagate neighborhood information, and (iii) lacking the capability to learn physical evolution laws, which lead to poor performance of the models. To tackle these challenges, we propose D\u0000<inline-formula><tex-math>$^{3}$</tex-math></inline-formula>\u0000HP, a \u0000<u>D</u>\u0000ual-view \u0000<u>D</u>\u0000esynchronization hypergraph learning for arbitrary-order \u0000<u>D</u>\u0000ynamic \u0000<u>H</u>\u0000yperedge \u0000<u>P</u>\u0000rediction. Specifically, D\u0000<inline-formula><tex-math>$^{3}$</tex-math></inline-formula>\u0000HP extracts the dynamic higher-order and lower-order features of hyperedges separately through an elastic hypergraph neural network (EHGNN) and an alternate desynchronization graph convolutional network (ADGCN) at each time snapshot. EHGNN is designed to incrementally mine the implicit higher-order relations and propagate neighborhood information. Moreover, ADGCN aims to combine GCN with desynchronization learining to learn the physical evolution of lower-order relations and alleviate the over-smoothing problem. Further, we improve the prediction performance of the model by rationally fusing the features learned from the dual views. Extensive experiments on 8 dynamic higher-order networks demonstrate that D\u0000<inline-formula><tex-math>$^{3}$</tex-math></inline-formula>\u0000HP outperforms 14 state-of-the-art baselines.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"597-612"},"PeriodicalIF":8.9,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-29DOI: 10.1109/TKDE.2024.3509480
Xuan Rao;Renhe Jiang;Shuo Shang;Lisi Chen;Peng Han;Bin Yao;Panos Kalnis
Next point-of-interest (POI) recommendation predicts user’s next movement and facilitates location-based applications such as destination suggestion and travel planning. State-of-the-art (SOTA) methods learn an adaptive graph from user trajectories and compute POI representations using graph neural networks (GNNs). However, a single graph cannot capture the diverse dependencies among the POIs (e.g., geographical proximity and transition frequency). To tackle this limitation, we propose the Adaptive Graph Contrastive Learning (AGCL) framework. AGCL constructs multiple adaptive graphs, each modeling a kind of POI dependency and producing one POI representation; and the POI representations from different graphs are merged into a multi-facet representation that encodes comprehensive information. To train the POI representations, we tailor a graph-based contrastive learning, which encourages the representations of similar POIs to align and dissimilar POIs to differentiate. Moreover, to learn the sequential regularities of user trajectories, we design an attention mechanism to integrate spatial-temporal information into the POI representations. An explicit spatial-temporal bias is also employed to adjust the predictions for enhanced accuracy. We compare AGCL with 10 state-of-the-art baselines on 3 datasets. The results show that AGCL outperforms all baselines and achieves an improvement of 10.14% over the best performing baseline in average accuracy.
{"title":"Next Point-of-Interest Recommendation With Adaptive Graph Contrastive Learning","authors":"Xuan Rao;Renhe Jiang;Shuo Shang;Lisi Chen;Peng Han;Bin Yao;Panos Kalnis","doi":"10.1109/TKDE.2024.3509480","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3509480","url":null,"abstract":"<italic>Next point-of-interest (POI) recommendation</i> predicts user’s next movement and facilitates location-based applications such as destination suggestion and travel planning. State-of-the-art (SOTA) methods learn an adaptive graph from user trajectories and compute POI representations using graph neural networks (GNNs). However, a single graph cannot capture the <italic>diverse dependencies</i> among the POIs (e.g., geographical proximity and transition frequency). To tackle this limitation, we propose the <underline><i>A</i></u><italic>daptive</i> <underline><i>G</i></u><italic>raph</i> <underline><i>C</i></u><italic>ontrastive</i> <underline><i>L</i></u><italic>earning</i> (<italic>AGCL</i>) framework. AGCL constructs multiple adaptive graphs, each modeling a kind of POI dependency and producing one POI representation; and the POI representations from different graphs are merged into a <italic>multi-facet representation</i> that encodes comprehensive information. To train the POI representations, we tailor a <italic>graph-based contrastive learning</i>, which encourages the representations of similar POIs to align and dissimilar POIs to differentiate. Moreover, to learn the sequential regularities of user trajectories, we design an attention mechanism to integrate spatial-temporal information into the POI representations. An explicit <italic>spatial-temporal bias</i> is also employed to adjust the predictions for enhanced accuracy. We compare AGCL with 10 state-of-the-art baselines on 3 datasets. The results show that AGCL outperforms all baselines and achieves an improvement of 10.14% over the best performing baseline in average accuracy.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1366-1379"},"PeriodicalIF":8.9,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-28DOI: 10.1109/TKDE.2024.3509267
Qiang Gao;Zhengxiang Liu;Li Huang;Kunpeng Zhang;Jun Wang;Guisong Liu
Optimizing stock selection through stock ranking is one of the critical but intricate tasks in quantitative trading areas because of the non-stationary dynamics and complicated interdependencies behind stock markets. Recent studies have made efforts to model historical market movements to enhance stock selection. However, they primarily borrowed the spirit of time series modeling and sought to build a deterministic paradigm without considering the uncertain fluctuations. In addition, some of these studies tailor to explore stock correlations from a predefined (e.g., binary) graph structure and use explicitly simple relations (such as first-order relations) to guide evolving interactions. Nevertheless, aggregating predefined but shallow relationships to collaborate with stock movements may affect selection generalizability and increase the risk of portfolio failure. This study introduces a novel R elational stock selection framework via probabilistic S tate S pace L earning (or RSSL ) for stock selection. Specifically, RSSL first attempts to build a tree-based structure to explicitly expose higher-order relations in the stock market, primarily by discovering a hierarchical delineation of ties between stocks. Whereafter, it couples with time-varying movements via an attention mechanism to smoothly explore the interactive correlations among different stocks. Inspired by recent state space models (SSM) in probabilistic Bayesian learning, we devise a Probabilistic Kalman Network (PKNet) with uncertainty estimates to recursively simulate ever-changing stock volatility, enabling more promising return-risk trade-offs. The experimental results on several real-world stock market datasets demonstrate that RSSL outperforms several representative baseline methods by a significant margin.
{"title":"Relational Stock Selection via Probabilistic State Space Learning","authors":"Qiang Gao;Zhengxiang Liu;Li Huang;Kunpeng Zhang;Jun Wang;Guisong Liu","doi":"10.1109/TKDE.2024.3509267","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3509267","url":null,"abstract":"Optimizing stock selection through stock ranking is one of the critical but intricate tasks in quantitative trading areas because of the non-stationary dynamics and complicated interdependencies behind stock markets. Recent studies have made efforts to model historical market movements to enhance stock selection. However, they primarily borrowed the spirit of time series modeling and sought to build a deterministic paradigm without considering the uncertain fluctuations. In addition, some of these studies tailor to explore stock correlations from a predefined (e.g., binary) graph structure and use explicitly simple relations (such as first-order relations) to guide evolving interactions. Nevertheless, aggregating predefined but shallow relationships to collaborate with stock movements may affect selection generalizability and increase the risk of portfolio failure. This study introduces a novel \u0000<bold>R</b>\u0000elational stock selection framework via probabilistic \u0000<bold>S</b>\u0000tate \u0000<bold>S</b>\u0000pace \u0000<bold>L</b>\u0000earning (or \u0000<bold>RSSL</b>\u0000) for stock selection. Specifically, RSSL first attempts to build a tree-based structure to explicitly expose higher-order relations in the stock market, primarily by discovering a hierarchical delineation of ties between stocks. Whereafter, it couples with time-varying movements via an attention mechanism to smoothly explore the interactive correlations among different stocks. Inspired by recent state space models (SSM) in probabilistic Bayesian learning, we devise a Probabilistic Kalman Network (PKNet) with uncertainty estimates to recursively simulate ever-changing stock volatility, enabling more promising return-risk trade-offs. The experimental results on several real-world stock market datasets demonstrate that RSSL outperforms several representative baseline methods by a significant margin.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"865-880"},"PeriodicalIF":8.9,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Social recommendations leverage social networks to augment the performance of recommender systems. However, the critical task of denoising social information has not been thoroughly investigated in prior research. In this study, we introduce a hierarchical denoising robust social recommendation model to tackle noise at two levels: 1) intra-domain noise, resulting from user multi-faceted social trust relationships, and 2) inter-domain noise, stemming from the entanglement of the latent factors over heterogeneous relations (e.g., user-item interactions, user-user trust relationships). Specifically, our model advances a preference and social psychology-aware methodology for the fine-grained and multi-perspective estimation of tie strength within social networks. This serves as a precursor to an edge weight-guided edge pruning strategy that refines the model's diversity and robustness by dynamically filtering social ties. Additionally, we propose a user interest-aware cross-domain denoising gate, which not only filters noise during the knowledge transfer process but also captures the high-dimensional, nonlinear information prevalent in social domains. We conduct extensive experiments on three real-world datasets to validate the effectiveness of our proposed model against state-of-the-art baselines. We perform empirical studies on synthetic datasets to validate the strong robustness of our proposed model.
{"title":"Hierarchical Denoising for Robust Social Recommendation","authors":"Zheng Hu;Satoshi Nakagawa;Yan Zhuang;Jiawen Deng;Shimin Cai;Tao Zhou;Fuji Ren","doi":"10.1109/TKDE.2024.3508778","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3508778","url":null,"abstract":"Social recommendations leverage social networks to augment the performance of recommender systems. However, the critical task of denoising social information has not been thoroughly investigated in prior research. In this study, we introduce a hierarchical denoising robust social recommendation model to tackle noise at two levels: 1) intra-domain noise, resulting from user multi-faceted social trust relationships, and 2) inter-domain noise, stemming from the entanglement of the latent factors over heterogeneous relations (e.g., user-item interactions, user-user trust relationships). Specifically, our model advances a preference and social psychology-aware methodology for the fine-grained and multi-perspective estimation of tie strength within social networks. This serves as a precursor to an edge weight-guided edge pruning strategy that refines the model's diversity and robustness by dynamically filtering social ties. Additionally, we propose a user interest-aware cross-domain denoising gate, which not only filters noise during the knowledge transfer process but also captures the high-dimensional, nonlinear information prevalent in social domains. We conduct extensive experiments on three real-world datasets to validate the effectiveness of our proposed model against state-of-the-art baselines. We perform empirical studies on synthetic datasets to validate the strong robustness of our proposed model.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"739-753"},"PeriodicalIF":8.9,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-28DOI: 10.1109/TKDE.2024.3508064
Kai Wang;Dan Lin;Siqiang Luo
We study Graph Neural Networks (GNNs)-based embedding techniques for knowledge graph (KG) reasoning. For the first time, we link the path redundancy issue in the state-of-the-art path encoding-based models to the transformation error in model training, which brings us new theoretical insights into KG reasoning, as well as high efficacy in practice. On the theoretical side, we analyze the entropy of transformation error in KG paths and point out query-specific redundant paths causing entropy increases. These findings guide us to maintain the shortest paths and remove redundant paths for minimized-entropy message passing. To achieve this goal, on the practical side, we propose an efficient Graph Percolation process motivated by the percolation phenomenon in Fluid Mechanics, and design a lightweight GNN-based KG reasoning framework called Graph Percolation Embeddings (GraPE)1. GraPE outperforms state-of-the-art methods in both transductive and inductive reasoning tasks, while requiring fewer training parameters and less inference time.
{"title":"Graph Percolation Embeddings for Efficient Knowledge Graph Inductive Reasoning","authors":"Kai Wang;Dan Lin;Siqiang Luo","doi":"10.1109/TKDE.2024.3508064","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3508064","url":null,"abstract":"We study Graph Neural Networks (GNNs)-based embedding techniques for knowledge graph (KG) reasoning. For the first time, we link the path redundancy issue in the state-of-the-art path encoding-based models to the transformation error in model training, which brings us new theoretical insights into KG reasoning, as well as high efficacy in practice. On the theoretical side, we analyze the entropy of transformation error in KG paths and point out query-specific redundant paths causing entropy increases. These findings guide us to maintain the shortest paths and remove redundant paths for minimized-entropy message passing. To achieve this goal, on the practical side, we propose an efficient Graph Percolation process motivated by the percolation phenomenon in Fluid Mechanics, and design a lightweight GNN-based KG reasoning framework called Graph Percolation Embeddings (<italic>GraPE</i>)<sup>1</sup>. GraPE outperforms state-of-the-art methods in both transductive and inductive reasoning tasks, while requiring fewer training parameters and less inference time.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1198-1212"},"PeriodicalIF":8.9,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：