Pub Date : 2024-11-07DOI: 10.1109/TKDE.2024.3493374
Zengmao Wang;Yunzhen Feng;Xin Zhang;Renjie Yang;Bo Du
Multi-modal contents have proven to be the powerful knowledge for recommendation tasks. Most state-of-the-art multi-modal recommendation methods mainly focus on aligning the semantic spaces of different modalities to enhance the item representations and do not pay much attention on the relevant knowledge in the multi-modalities for recommendation, resulting in that the positive effects of the relevant knowledge is reduced and the improvement of recommendation performance is limited. In this paper, we propose a multi-modal correction network termed MMCN to enhance the item representation with the important semantic knowledge in each modality by a residual structure with attention mechanisms and a hierarchical contrastive learning framework. The residual information is obtained through self-attention and cross-attention, which can learn the relevant knowledge across different modalities effectively. While hierarchical contrastive learning further captures the relevant knowledge not only at the feature level but also at the element-wise level with a matrix. Extensive experiments on three large-scale real-world datasets show the superiority of MMCN over state-of-the-art multi-modal recommendation methods.
{"title":"Multi-Modal Correction Network for Recommendation","authors":"Zengmao Wang;Yunzhen Feng;Xin Zhang;Renjie Yang;Bo Du","doi":"10.1109/TKDE.2024.3493374","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3493374","url":null,"abstract":"Multi-modal contents have proven to be the powerful knowledge for recommendation tasks. Most state-of-the-art multi-modal recommendation methods mainly focus on aligning the semantic spaces of different modalities to enhance the item representations and do not pay much attention on the relevant knowledge in the multi-modalities for recommendation, resulting in that the positive effects of the relevant knowledge is reduced and the improvement of recommendation performance is limited. In this paper, we propose a multi-modal correction network termed MMCN to enhance the item representation with the important semantic knowledge in each modality by a residual structure with attention mechanisms and a hierarchical contrastive learning framework. The residual information is obtained through self-attention and cross-attention, which can learn the relevant knowledge across different modalities effectively. While hierarchical contrastive learning further captures the relevant knowledge not only at the feature level but also at the element-wise level with a matrix. Extensive experiments on three large-scale real-world datasets show the superiority of MMCN over state-of-the-art multi-modal recommendation methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"810-822"},"PeriodicalIF":8.9,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940776","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 : 2024-11-06DOI: 10.1109/TKDE.2024.3492339
Aditi Gupta;Adeiza James Onumanyi;Satyadev Ahlawat;Yamuna Prasad;Virendra Singh
Change point detection (CPD) is a valuable technique in time series (TS) analysis, which allows for the automatic detection of abrupt variations within the TS. It is often useful in applications such as fault, anomaly, and intrusion detection systems. However, the inherent unpredictability and fluctuations in many real-time data sources pose a challenge for existing contemporary CPD techniques, leading to inconsistent performance across diverse real-time TS with varying characteristics. To address this challenge, we have developed a novel and robust online CPD algorithm constructed from the principle of discriminant analysis and based upon a newly proposed between-class average and variance evaluation approach, termed B-CAVE. Our B-CAVE algorithm features a unique change point measure, which has only one tunable parameter (i.e. the window size) in its computational process. We have also proposed a new evaluation metric that integrates time delay and the false alarm error towards effectively comparing the performance of different CPD methods in the literature. To validate the effectiveness of our method, we conducted experiments using both synthetic and real datasets, demonstrating the superior performance of the B-CAVE algorithm over other prominent existing techniques.
{"title":"B-CAVE: A Robust Online Time Series Change Point Detection Algorithm Based on the Between-Class Average and Variance Evaluation Approach","authors":"Aditi Gupta;Adeiza James Onumanyi;Satyadev Ahlawat;Yamuna Prasad;Virendra Singh","doi":"10.1109/TKDE.2024.3492339","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3492339","url":null,"abstract":"Change point detection (CPD) is a valuable technique in time series (TS) analysis, which allows for the automatic detection of abrupt variations within the TS. It is often useful in applications such as fault, anomaly, and intrusion detection systems. However, the inherent unpredictability and fluctuations in many real-time data sources pose a challenge for existing contemporary CPD techniques, leading to inconsistent performance across diverse real-time TS with varying characteristics. To address this challenge, we have developed a novel and robust online CPD algorithm constructed from the principle of discriminant analysis and based upon a newly proposed between-class average and variance evaluation approach, termed B-CAVE. Our B-CAVE algorithm features a unique change point measure, which has only one tunable parameter (i.e. the window size) in its computational process. We have also proposed a new evaluation metric that integrates time delay and the false alarm error towards effectively comparing the performance of different CPD methods in the literature. To validate the effectiveness of our method, we conducted experiments using both synthetic and real datasets, demonstrating the superior performance of the B-CAVE algorithm over other prominent existing techniques.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 1","pages":"75-88"},"PeriodicalIF":8.9,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142797953","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 : 2024-11-06DOI: 10.1109/TKDE.2024.3488375
Ruidong Wang;Liang Xi;Fengbin Zhang;Haoyi Fan;Xu Yu;Lei Liu;Shui Yu;Victor C. M. Leung
In unsupervised graph anomaly detection, existing methods usually focus on detecting outliers by learning local context information of nodes, while often ignoring the importance of global context. However, global context information can provide more comprehensive relationship information between nodes in the network. By considering the structure of the entire network, detection methods are able to identify potential dependencies and interaction patterns between nodes, which is crucial for anomaly detection. Therefore, we propose an innovative graph anomaly detection framework, termed CoCo (Context Correlation Discrepancy Analysis), which detects anomalies by meticulously evaluating variances in correlations. Specifically, CoCo leverages the strengths of Transformers in sequence processing to effectively capture both global and local contextual features of nodes by aggregating neighbor features at various hops. Subsequently, a correlation analysis module is employed to maximize the correlation between local and global contexts of each normal node. Unseen anomalies are ultimately detected by measuring the discrepancy in the correlation of nodes’ contextual features. Extensive experiments conducted on six datasets with synthetic outliers and five datasets with organic outliers have demonstrated the significant effectiveness of CoCo compared to existing methods.
{"title":"Context Correlation Discrepancy Analysis for Graph Anomaly Detection","authors":"Ruidong Wang;Liang Xi;Fengbin Zhang;Haoyi Fan;Xu Yu;Lei Liu;Shui Yu;Victor C. M. Leung","doi":"10.1109/TKDE.2024.3488375","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3488375","url":null,"abstract":"In unsupervised graph anomaly detection, existing methods usually focus on detecting outliers by learning local context information of nodes, while often ignoring the importance of global context. However, global context information can provide more comprehensive relationship information between nodes in the network. By considering the structure of the entire network, detection methods are able to identify potential dependencies and interaction patterns between nodes, which is crucial for anomaly detection. Therefore, we propose an innovative graph anomaly detection framework, termed CoCo (Context Correlation Discrepancy Analysis), which detects anomalies by meticulously evaluating variances in correlations. Specifically, CoCo leverages the strengths of Transformers in sequence processing to effectively capture both global and local contextual features of nodes by aggregating neighbor features at various hops. Subsequently, a correlation analysis module is employed to maximize the correlation between local and global contexts of each normal node. Unseen anomalies are ultimately detected by measuring the discrepancy in the correlation of nodes’ contextual features. Extensive experiments conducted on six datasets with synthetic outliers and five datasets with organic outliers have demonstrated the significant effectiveness of CoCo compared to existing methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 1","pages":"174-187"},"PeriodicalIF":8.9,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142797997","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}
As the representative density-based clustering algorithm, density peaks clustering (DPC) has wide recognition, and many improved algorithms and applications have been extended from it. However, the DPC involving privacy protection has not been deeply studied. In addition, there is still room for improvement in the selection of centers and allocation methods of DPC. To address these issues, vertical federated density peaks clustering under nonlinear mapping (VFDPC) is proposed to address privacy protection issues in vertically partitioned data. Firstly, a hybrid encryption privacy protection mechanism is proposed to protect the merging process of distance matrices generated by client data. Secondly, according to the merged distance matrix, a more effective cluster merging under nonlinear mapping is proposed to ameliorate the process of DPC. Results on man-made, real, and multi-view data fully prove the improvement of VFDPC on clustering accuracy.
{"title":"Vertical Federated Density Peaks Clustering Under Nonlinear Mapping","authors":"Chao Li;Shifei Ding;Xiao Xu;Lili Guo;Ling Ding;Xindong Wu","doi":"10.1109/TKDE.2024.3487534","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3487534","url":null,"abstract":"As the representative density-based clustering algorithm, density peaks clustering (DPC) has wide recognition, and many improved algorithms and applications have been extended from it. However, the DPC involving privacy protection has not been deeply studied. In addition, there is still room for improvement in the selection of centers and allocation methods of DPC. To address these issues, vertical federated density peaks clustering under nonlinear mapping (VFDPC) is proposed to address privacy protection issues in vertically partitioned data. Firstly, a hybrid encryption privacy protection mechanism is proposed to protect the merging process of distance matrices generated by client data. Secondly, according to the merged distance matrix, a more effective cluster merging under nonlinear mapping is proposed to ameliorate the process of DPC. Results on man-made, real, and multi-view data fully prove the improvement of VFDPC on clustering accuracy.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"1004-1017"},"PeriodicalIF":8.9,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940881","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 : 2024-11-05DOI: 10.1109/TKDE.2024.3491996
Zhaoheng Huang;Yutao Zhu;Zhicheng Dou;Ji-Rong Wen
In search sessions, a series of interactions in the context has been proven to be advantageous in capturing users’ search intents. Existing studies show that designing pre-training tasks and data augmentation strategies for session search improves the robustness and generalizability of the model. However, such data augmentation strategies only focus on changing the original session structure to learn a better representation. Ignoring information from outside the session, users’ diverse and complex intents cannot be learned well by simply reordering and deleting historical behaviors, proving that such strategies are limited and inadequate. In order to solve the problem of insufficient modeling under complex user intents, we propose exploiting information outside the original session. More specifically, in this paper, we sample queries and documents from the global click-on and follow-up session graph, alter an original session with these samples, and construct a new session that shares a similar user intent with the original one. Specifically, we design four data augmentation strategies based on session graphs in view of both one-hop and multi-hop structures to sample intent-associated query/document nodes. Experiments conducted on three large-scale public datasets demonstrate that our model outperforms the existing ad-hoc and context-aware document ranking models.
{"title":"CAGS: Context-Aware Document Ranking With Contrastive Graph Sampling","authors":"Zhaoheng Huang;Yutao Zhu;Zhicheng Dou;Ji-Rong Wen","doi":"10.1109/TKDE.2024.3491996","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3491996","url":null,"abstract":"In search sessions, a series of interactions in the context has been proven to be advantageous in capturing users’ search intents. Existing studies show that designing pre-training tasks and data augmentation strategies for session search improves the robustness and generalizability of the model. However, such data augmentation strategies only focus on changing the original session structure to learn a better representation. Ignoring information from outside the session, users’ diverse and complex intents cannot be learned well by simply reordering and deleting historical behaviors, proving that such strategies are limited and inadequate. In order to solve the problem of insufficient modeling under complex user intents, we propose exploiting information outside the original session. More specifically, in this paper, we sample queries and documents from the global click-on and follow-up session graph, alter an original session with these samples, and construct a new session that shares a similar user intent with the original one. Specifically, we design four data augmentation strategies based on session graphs in view of both one-hop and multi-hop structures to sample intent-associated query/document nodes. Experiments conducted on three large-scale public datasets demonstrate that our model outperforms the existing ad-hoc and context-aware document ranking models.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 1","pages":"89-101"},"PeriodicalIF":8.9,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142797963","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}
Knowledge graph embedding is efficient method for reasoning over known facts and inferring missing links. Existing methods are mainly triplet-based or graph-based. Triplet-based approaches learn the embedding of missing entities by a single triple only. They ignore the fact that the knowledge graph is essentially a graph structure. Graph-based methods consider graph structure information but ignore the contextual information of nodes in the knowledge graph, making them unable to discern valuable entity (relation) information. In response to the above limitations, we propose a general graph transformer framework for knowledge graph embedding (TGformer). It is the first to use a graph transformer to build knowledge embeddings with triplet-level and graph-level structural features in the static and temporal knowledge graph. Specifically, a context-level subgraph is constructed for each predicted triplet, which models the relation between triplets with the same entity. Afterward, we design a knowledge graph transformer network (KGTN) to fully explore multi-structural features in knowledge graphs, including triplet-level and graph-level, boosting the model to understand entities (relations) in different contexts. Finally, semantic matching is adopted to select the entity with the highest score. Experimental results on several public knowledge graph datasets show that our method can achieve state-of-the-art performance in link prediction.
{"title":"TGformer: A Graph Transformer Framework for Knowledge Graph Embedding","authors":"Fobo Shi;Duantengchuan Li;Xiaoguang Wang;Bing Li;Xindong Wu","doi":"10.1109/TKDE.2024.3486747","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3486747","url":null,"abstract":"Knowledge graph embedding is efficient method for reasoning over known facts and inferring missing links. Existing methods are mainly triplet-based or graph-based. Triplet-based approaches learn the embedding of missing entities by a single triple only. They ignore the fact that the knowledge graph is essentially a graph structure. Graph-based methods consider graph structure information but ignore the contextual information of nodes in the knowledge graph, making them unable to discern valuable entity (relation) information. In response to the above limitations, we propose a general graph transformer framework for knowledge graph embedding (TGformer). It is the first to use a graph transformer to build knowledge embeddings with triplet-level and graph-level structural features in the static and temporal knowledge graph. Specifically, a context-level subgraph is constructed for each predicted triplet, which models the relation between triplets with the same entity. Afterward, we design a knowledge graph transformer network (KGTN) to fully explore multi-structural features in knowledge graphs, including triplet-level and graph-level, boosting the model to understand entities (relations) in different contexts. Finally, semantic matching is adopted to select the entity with the highest score. Experimental results on several public knowledge graph datasets show that our method can achieve state-of-the-art performance in link prediction.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 1","pages":"526-541"},"PeriodicalIF":8.9,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810294","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}
In recommender systems, it is frequently presumed that missing ratings adhere to a missing at random (MAR) mechanism, implying the absence of ratings is independent of their potential values. However, this assumption fails to hold in real-world scenarios, where users are inclined to rate items they either strongly favor or disfavor, introducing a missing not at random (MNAR) scenario. To tackle this issue, prior researchers have utilized explicit MAR feedbacks to infer the propensities of unobserved, implicit MNAR feedbacks. Nonetheless, acquiring explicit MAR feedbacks is resource-intensive and time-consuming and may not reflect users’ true preferences. Furthermore, most methods have only been tested on synthetic or small-scale datasets, thus their applicability and effectiveness in real-world settings without MAR feedbacks remain unclear. Along these lines, we aim to predict MNAR ratings without MAR prior propensities by exploring the consistency between MAR and MNAR feedbacks and narrowing the gap between them. From the empirical study and preliminary experiment, we hypothesize that user preferences can be treated as the common prior propensity for both MAR and MNAR generative processes. In this way, we extend this hypothesis to a more general MNAR scenario: user preferences learned from MNAR can partially substitute for the prior propensities derived from MAR feedbacks for MNAR recommendation tasks. To validate our hypothesis and approach, we develop a lightweight iterative probabilistic matrix factorization framework (lightIPMF) as a practical method of our methodology, utilizing user preferences extracted from MNAR, not MAR, to estimate MNAR feedbacks. Finally, the experimental results show that modeling user preferences can effectively improve MNAR feedback estimation without MAR feedback, and our proposed lightIPMF outperforms the state-of-the-art MNAR methods in predicting MNAR feedbacks.
{"title":"Learning Without Missing-At-Random Prior Propensity-A Generative Approach for Recommender Systems","authors":"Yuanbo Xu;Fuzhen Zhuang;En Wang;Chaozhuo Li;Jie Wu","doi":"10.1109/TKDE.2024.3490593","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3490593","url":null,"abstract":"In recommender systems, it is frequently presumed that missing ratings adhere to a missing at random (MAR) mechanism, implying the absence of ratings is independent of their potential values. However, this assumption fails to hold in real-world scenarios, where users are inclined to rate items they either strongly favor or disfavor, introducing a missing not at random (MNAR) scenario. To tackle this issue, prior researchers have utilized explicit MAR feedbacks to infer the propensities of unobserved, implicit MNAR feedbacks. Nonetheless, acquiring explicit MAR feedbacks is resource-intensive and time-consuming and may not reflect users’ true preferences. Furthermore, most methods have only been tested on synthetic or small-scale datasets, thus their applicability and effectiveness in real-world settings without MAR feedbacks remain unclear. Along these lines, we aim to predict MNAR ratings without MAR prior propensities by exploring the consistency between MAR and MNAR feedbacks and narrowing the gap between them. From the empirical study and preliminary experiment, we hypothesize that \u0000<italic>user preferences</i>\u0000 can be treated as the common prior propensity for both MAR and MNAR generative processes. In this way, we extend this hypothesis to a more general MNAR scenario: user preferences learned from MNAR can partially substitute for the prior propensities derived from MAR feedbacks for MNAR recommendation tasks. To validate our hypothesis and approach, we develop a lightweight iterative probabilistic matrix factorization framework (lightIPMF) as a practical method of our methodology, utilizing user preferences extracted from MNAR, not MAR, to estimate MNAR feedbacks. Finally, the experimental results show that modeling user preferences can effectively improve MNAR feedback estimation without MAR feedback, and our proposed lightIPMF outperforms the state-of-the-art MNAR methods in predicting MNAR feedbacks.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"754-765"},"PeriodicalIF":8.9,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940962","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 : 2024-11-04DOI: 10.1109/TKDE.2024.3486326
Yang Cao;Shuo Shang;Jun Wang;Wei Zhang
This paper explores explaining session-based recommendation (SR) by path reasoning. Current SR models emphasize accuracy but lack explainability, while traditional path reasoning prioritizes knowledge graph exploration, ignoring sequential patterns present in the session history. Therefore, we propose a generalized hierarchical reinforcement learning framework for SR, which improves the explainability of existing SR models via Path Reasoning, namely PR4SR. Considering the different importance of items to the session, we design the session-level agent to select the items in the session as the starting nodes for path reasoning and the path-level agent to perform path reasoning. In particular, we design a multi-target reward mechanism to adapt to the skip behaviors of sequential patterns in SR and introduce path midpoint reward to enhance the exploration efficiency and accuracy in knowledge graphs. To improve the knowledge graph’s completeness and diversify the paths of explanation, we incorporate extracted feature information from images into the knowledge graph. We instantiate PR4SR in five state-of-the-art SR models (i.e., GRU4REC, NARM, GCSAN, SR-GNN, SASRec) and compare it with other explainable SR frameworks to demonstrate the effectiveness of PR4SR for recommendation and explanation tasks through extensive experiments with these approaches on four datasets.
{"title":"Explainable Session-Based Recommendation via Path Reasoning","authors":"Yang Cao;Shuo Shang;Jun Wang;Wei Zhang","doi":"10.1109/TKDE.2024.3486326","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3486326","url":null,"abstract":"This paper explores explaining session-based recommendation (SR) by path reasoning. Current SR models emphasize accuracy but lack explainability, while traditional path reasoning prioritizes knowledge graph exploration, ignoring sequential patterns present in the session history. Therefore, we propose a generalized hierarchical reinforcement learning framework for SR, which improves the explainability of existing SR models via Path Reasoning, namely PR4SR. Considering the different importance of items to the session, we design the session-level agent to select the items in the session as the starting nodes for path reasoning and the path-level agent to perform path reasoning. In particular, we design a multi-target reward mechanism to adapt to the skip behaviors of sequential patterns in SR and introduce path midpoint reward to enhance the exploration efficiency and accuracy in knowledge graphs. To improve the knowledge graph’s completeness and diversify the paths of explanation, we incorporate extracted feature information from images into the knowledge graph. We instantiate PR4SR in five state-of-the-art SR models (i.e., GRU4REC, NARM, GCSAN, SR-GNN, SASRec) and compare it with other explainable SR frameworks to demonstrate the effectiveness of PR4SR for recommendation and explanation tasks through extensive experiments with these approaches on four datasets.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 1","pages":"278-290"},"PeriodicalIF":8.9,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142797899","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 : 2024-11-04DOI: 10.1109/TKDE.2024.3490843
Dezheng Wang;Rongjie Liu;Congyan Chen;Shihua Li
Short-term time series forecasting is pivotal in various scientific and industrial fields. Recent advancements in deep learning-based technologies have significantly improved the efficiency and accuracy of short-term time series modeling. Despite advancements, current time short-term series forecasting methods typically emphasize modeling dependencies across time stamps but frequently overlook inter-variable dependencies, which is crucial for multivariate forecasting. We propose a multi patterns memory model discovering various dependency patterns for short-term multivariate time series forecasting to fill the gap. The proposed model is structured around two key components: the short-term memory block and the long-term memory block. These networks are distinctively characterized by their use of asymmetric convolution, each tailored to process the various spatial-temporal dependencies among data. Experimental results show that the proposed model demonstrates competitive performance over the other time series forecasting methods across five benchmark datasets, likely thanks to the asymmetric structure, which can effectively extract the underlying various spatial-temporal dependencies among data.
{"title":"MPM: Multi Patterns Memory Model for Short-Term Time Series Forecasting","authors":"Dezheng Wang;Rongjie Liu;Congyan Chen;Shihua Li","doi":"10.1109/TKDE.2024.3490843","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3490843","url":null,"abstract":"Short-term time series forecasting is pivotal in various scientific and industrial fields. Recent advancements in deep learning-based technologies have significantly improved the efficiency and accuracy of short-term time series modeling. Despite advancements, current time short-term series forecasting methods typically emphasize modeling dependencies across time stamps but frequently overlook inter-variable dependencies, which is crucial for multivariate forecasting. We propose a multi patterns memory model discovering various dependency patterns for short-term multivariate time series forecasting to fill the gap. The proposed model is structured around two key components: the short-term memory block and the long-term memory block. These networks are distinctively characterized by their use of asymmetric convolution, each tailored to process the various spatial-temporal dependencies among data. Experimental results show that the proposed model demonstrates competitive performance over the other time series forecasting methods across five benchmark datasets, likely thanks to the asymmetric structure, which can effectively extract the underlying various spatial-temporal dependencies among data.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 1","pages":"438-448"},"PeriodicalIF":8.9,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810297","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 : 2024-11-01DOI: 10.1109/TKDE.2024.3489796
Xiao Li;Huan Li;Hua Lu;Christian S. Jensen
In large venues like shopping malls and airports, knowledge on the indoor populations fuels applications such as business analytics, venue management, and safety control. In this work, we provide means of modeling populations in partitions of indoor space offline and of monitoring indoor populations continuously, by using indoor positioning data. However, the low-sampling rates of indoor positioning render the data temporally and spatially sparse, which in turn renders the offline capture of indoor populations challenging. It is even more challenging to continuously monitor indoor populations, as positioning data may be missing or not ready yet at the current moment. To address these challenges, we first enable probabilistic modeling of populations in indoor space partitions as Normal distributions. Based on that, we propose two learning-based estimators for on-the-fly prediction of population distributions. Leveraging the prediction-based schemes, we provide a unified continuous query processing framework for a type of query that enables continuous monitoring of populated partitions. The framework encompasses caching and result validity mechanisms to reduce cost and maintain monitoring effectiveness. Extensive experiments on two real data sets show that the proposed estimators are able to outperform the state-of-the-art alternatives and that the query processing framework is effective and efficient.
{"title":"Modeling and Monitoring of Indoor Populations Using Sparse Positioning Data","authors":"Xiao Li;Huan Li;Hua Lu;Christian S. Jensen","doi":"10.1109/TKDE.2024.3489796","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3489796","url":null,"abstract":"In large venues like shopping malls and airports, knowledge on the indoor populations fuels applications such as business analytics, venue management, and safety control. In this work, we provide means of modeling populations in partitions of indoor space offline and of monitoring indoor populations continuously, by using indoor positioning data. However, the low-sampling rates of indoor positioning render the data temporally and spatially sparse, which in turn renders the offline capture of indoor populations challenging. It is even more challenging to continuously monitor indoor populations, as positioning data may be missing or not ready yet at the current moment. To address these challenges, we first enable probabilistic modeling of populations in indoor space partitions as Normal distributions. Based on that, we propose two learning-based estimators for on-the-fly prediction of population distributions. Leveraging the prediction-based schemes, we provide a unified continuous query processing framework for a type of query that enables continuous monitoring of populated partitions. The framework encompasses caching and result validity mechanisms to reduce cost and maintain monitoring effectiveness. Extensive experiments on two real data sets show that the proposed estimators are able to outperform the state-of-the-art alternatives and that the query processing framework is effective and efficient.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 2","pages":"794-809"},"PeriodicalIF":8.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940883","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：