Yang Zhang;Fuli Feng;Jizhi Zhang;Keqin Bao;Qifan Wang;Xiangnan He
{"title":"CoLLM: Integrating Collaborative Embeddings Into Large Language Models for Recommendation","authors":"Yang Zhang;Fuli Feng;Jizhi Zhang;Keqin Bao;Qifan Wang;Xiangnan He","doi":"10.1109/TKDE.2025.3540912","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3540912","url":null,"abstract":"Leveraging Large Language Models as recommenders, referred to as LLMRec, is gaining traction and brings novel dynamics for modeling user preferences, particularly for cold-start users. However, existing LLMRec approaches primarily focus on text semantics and overlook the crucial aspect of incorporating collaborative information from user-item interactions, leading to potentially sub-optimal performance in warm-start scenarios. To ensure superior recommendations across both warm and cold scenarios, we introduce <italic>CoLLM</i>, an innovative LLMRec approach that explicitly integrates collaborative information for recommendations. CoLLM treats collaborative information as a distinct modality, directly encoding it from well-established traditional collaborative models, and then tunes a mapping module to align this collaborative information with the LLM's input text token space for recommendations. By externally integrating traditional models, CoLLM ensures effective collaborative information modeling without modifying the LLM itself, providing the flexibility to adopt diverse collaborative information modeling mechanisms. Extensive experimentation validates that CoLLM adeptly integrates collaborative information into LLMs, resulting in enhanced recommendation performance.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2329-2340"},"PeriodicalIF":8.9,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769452","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}
{"title":"Adaptive Reliable Defense Graph for Multi-Channel Robust GCN","authors":"Xiao Zhang;Peng Bao","doi":"10.1109/TKDE.2025.3538645","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3538645","url":null,"abstract":"Graph Convolutional Networks (GCNs) have demonstrated remarkable success in various graph-related tasks. However, recent studies show that GCNs are vulnerable to adversarial attacks on graph structures. Therefore, how to defend against such attacks has become a popular research topic. The current common defense methods face two main limitations: (1) From the data perspective, it may lead to suboptimal results since the structural information is ignored when distinguishing the perturbed edges. (2) From the model perspective, the defenders rely on the low-pass filter of the GCN, which is vulnerable during message passing. To overcome these limitations, this paper analyzes the characteristics of perturbed edges, and based on this we propose a robust defense framework, <italic>REDE</i>, to generate the adaptive <italic>Re</i>liable <italic>De</i>fense graph for multi-channel robust GCN. REDE first uses feature similarity and structure difference to discriminate perturbed edges and generates the defense graph by pruning them. Then REDE designs a multi-channel GCN, which can separately capture the information of different edges and high-order neighbors utilizing different frequency components. Leveraging this capability, the defense graph is adaptively updated at each layer, enhancing its reliability and improving prediction accuracy. Extensive experiments on four benchmark datasets demonstrate the enhanced performance and robustness of our proposed REDE over the state-of-the-art defense methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2226-2238"},"PeriodicalIF":8.9,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769536","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}
{"title":"Hypergraph Collaborative Filtering With Adaptive Augmentation of Graph Data for Recommendation","authors":"Jian Wang;Jianrong Wang;Di Jin;Xinglong Chang","doi":"10.1109/TKDE.2025.3539769","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3539769","url":null,"abstract":"Self-supervised tasks show significant advantages for node representation learning in recommender systems. This core idea of self-supervised task-based recommender systems depends on data augmentation to generate multi-view representations. However, there are two key challenges that are not well explored in existing self-supervised tasks: i) Restricted by the structure of the graph-based CF paradigm itself, the classical graph comparison learning architecture ignores the global structural information on the user-item interaction graph. ii) In a key part of existing contrast learning-random graph data enhancement schemes can significantly deteriorate model performance. To address these challenges, we propose a new hypergraph collaborative filtering with adaptive augmentation framework(HCFAA). It captures both local and global collaborative relationships on the user-item graph through a hypergraph-enhanced joint learning architecture. In particular, the designed adaptive structure-guided model ignores the noise introduced on unimportant edges, and thus learns the critical node information on the user-item graph. Comprehensive experimental studies on the Amazon dataset show that the method is effective, which provides an optimization scheme with a new perspective for the problems of key node loss in graph data enhancement and loss of higher-order structural information in GNN. The source code of our model can be available on <uri>https://github.com/RSnewbie/RS/tree/master/HCFAA</uri>.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2640-2651"},"PeriodicalIF":8.9,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769554","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}
{"title":"GAFExplainer: Global View Explanation of Graph Neural Networks Through Attribute Augmentation and Fusion Embedding","authors":"Wenya Hu;Jia Wu;Quan Qian","doi":"10.1109/TKDE.2025.3539989","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3539989","url":null,"abstract":"The excellent performance of graph neural networks (GNNs), which learn node representations by aggregating their neighborhood information, led to their use in various graph tasks. However, GNNs are black box models, the prediction results of which are difficult to understand directly. Although node attributes are vital for making predictions, previous studies have ignored their importance for explanation. This study presents GAFExplainer, a novel GNN explainer that emphasizes node attributes via attribute augmentation and fusion embedding. The former enhances node attribute encoding for more expressive masks, while the latter preserves the discrimination of node representations across different layers. Together, these modules significantly improve explanation performance. By training the explanatory network, a global view explanation of GNN models is obtained, and reasonably explainable subgraphs are available for new graphs, thus rendering the model well-generalizable. Multiple sets of experimental results on real and synthetic datasets demonstrate that the proposed model provides valid and accurate explanations. In the visual analysis, the explanations obtained by the proposed model are more comprehensible than those in existing work. Further, the fidelity evaluation and efficiency comparison reveal that with an average performance improvement of 8.9<inline-formula><tex-math>$% $</tex-math></inline-formula> compared with representative baselines, GAFExplainer achieves the best fidelity metrics while maintaining computational efficiency.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2569-2583"},"PeriodicalIF":8.9,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769563","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}
{"title":"Hierarchical Causal Discovery From Large-Scale Observed Variables","authors":"Rujia Shen;Muhan Li;Chao Zhao;Boran Wang;Yi Guan;Jie Liu;Jingchi Jiang","doi":"10.1109/TKDE.2025.3539788","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3539788","url":null,"abstract":"It is a long-standing question to discover causal relations from observed variables in many empirical sciences. However, current causal discovery methods are inefficient when dealing with large-scale observed variables due to challenges in conditional independence (CI) tests or complex computations of acyclicity, and may even fail altogether. To address the efficiency issue in causal discovery from large-scale observed variables, we propose a Hierarchical Causal Discovery (HCD) framework with a bilevel policy that handles this issue by boosting existing models. Specifically, the high-level policy first finds a causal cut set to partition observed variables into several causal clusters and releases the clusters to the low-level policy. The low-level policy applies any causal discovery method to process these causal clusters in parallel and obtain intra-cluster structures for subsequently inter-cluster structure merging in the high-level policy. To avoid missing inter-cluster edges, we theoretically demonstrate the feasibility of causal cluster cut and inter-cluster structure merging. We also prove the completeness and correctness of HCD for causal discovery. Experiments on both synthetic and real-world datasets demonstrate that HCD consistently and significantly enhances the efficiency and effectiveness of existing advanced methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2626-2639"},"PeriodicalIF":8.9,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769552","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}
{"title":"TaylorS: A Multi-Order Expansion Structure for Urban Spatio-Temporal Forecasting","authors":"Jianyang Qin;Yan Jia;Binxing Fang;Qing Liao","doi":"10.1109/TKDE.2025.3538857","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3538857","url":null,"abstract":"Although a variety of models have been proposed for urban spatio-temporal forecasting, most existing forecasting models are developed manually for specific tasks. By investigating the correlation between multi-order derivative and spatio-temporal data, we propose a generic yet simple plug-in structure, named <bold>TaylorS</b>, to improve the performance and generalization of existing forecasting models. The TaylorS converts the non-linear regression problem into a multi-order non-linear approximation problem by plugging a Taylor expansion into the forecasting task. To achieve this, we design a two-step training framework, including a training step and an adjusting step. During training, we train a given forecasting model as a base model to be equipped with prior knowledge. During adjusting, we fine-tune the base model while plugging an adjustment model into the base model. The adjustment model, as a multi-order expansion, takes the multi-order derivative of data to evaluate data uncertainty for further forecasting approximation and adjustment. Extensive experimental results demonstrate that the proposed TaylorS framework can consistently improve the performance of existing state-of-the-art methods and generalize these methods to different forecasting tasks.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"3030-3046"},"PeriodicalIF":8.9,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769519","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}
Siwei Wang;Xinwang Liu;Qing Liao;Yi Wen;En Zhu;Kunlun He
{"title":"Scalable Multi-View Graph Clustering With Cross-View Corresponding Anchor Alignment","authors":"Siwei Wang;Xinwang Liu;Qing Liao;Yi Wen;En Zhu;Kunlun He","doi":"10.1109/TKDE.2025.3538852","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3538852","url":null,"abstract":"Multi-view graph clustering (MVGC) explores pairwise correlations of entire instances and comprehensively aggregates diverse source information with optimal graph structure. One major issue of practical MVGC is the high time and space complexities prohibiting being applied on large-scale applications. As a promising solution of addressing large-scale problems, anchor-based strategy identifies small portion and key landmarks to serve as replacements for the entire dataset. Despite of its efficiency, anchors chosen across views may be semantically unaligned contrasting to naturally-aligned full sample setting, which may lead to the latter inappropriate graph fusion. Limited attention has been focused on the mentioned Multi-View Anchor-Unaligned Problem (MV-AUP) in the existing literature. In this paper, we first revisit existing multi-view anchor graph clustering frameworks and present the MV-AUP phenomenon. Then, we propose a novel <underline>M</u>ulti-view <underline>C</u>orresponding <underline>A</u>nchor <underline>G</u>raph <underline>A</u>lignment <underline>F</u>usion framework (MV-CAGAF), which elegantly solves MV-AUP with structural representation matching in multi-dimensional spaces. Further, we theoretically prove our proposed structural matching approach can be regarded as minimizing the EMD distance of the two relative anchor distributions. Based on this, we design the innovative multi-view anchor graph fusion paradigm with correspondence alignment, which inherits the linear sample complexity for scalable cross-view clustering. Our proposed MV-CAGAF achieves significant improvements with the help of the novel fusion framework on comprehensive benchmark datasets. Most importantly, the experimental results on both of the simulated and real-world datasets significantly prove the importance of cross-view alignment for large-scale multi-view clustering.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2932-2945"},"PeriodicalIF":8.9,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769367","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}
{"title":"TagRec: Temporal-Aware Graph Contrastive Learning With Theoretical Augmentation for Sequential Recommendation","authors":"Tianhao Peng;Haitao Yuan;Yongqi Zhang;Yuchen Li;Peihong Dai;Qunbo Wang;Senzhang Wang;Wenjun Wu","doi":"10.1109/TKDE.2025.3538706","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3538706","url":null,"abstract":"Sequential recommendation systems aim to predict the future behaviors of users based on their historical interactions. Despite the success of neural architectures like Transformer and Graph Neural Networks, these models often struggle with the inherent challenge of sparse data in accurately predicting future user behaviors. To alleviate the data sparsity problem, some methods leverage the contrastive learning to generate contrastive views, assuming the items appear discretely at the same time intervals and focusing on the sequence order. However, these approaches neglect the crucial temporal-aware collaborative patterns hidden within the user-item interactions, leading to a limited variety of contrastive pairs and less informative embeddings. The proposed framework, <bold><u>T</u></b>emporal-<bold><u>a</u></b>ware <bold><u>g</u></b>raph contrastive learning with theoretical guarantees for sequential <bold><u>Rec</u></b>ommendation (TagRec), integrates temporal-aware collaborative patterns with adaptive data augmentation to generate more informative user and item representations. TagRec employs a temporal-aware graph neural network to embed the original graph, then generates augmented graphs through the addition of interactions via latent user interest mining, the dropping of redundant interaction edges, and the perturbation of temporal information. Theoretical guarantees are provided that these augmentations enhance the graph’s utility. Extensive experiments on real-world datasets demonstrate the superiority of the proposed approach over the state-of-the-art recommendation methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"3015-3029"},"PeriodicalIF":8.9,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769538","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}
{"title":"Partitioned Dynamic Hub Labeling for Large Road Networks","authors":"Mengxuan Zhang;Xinjie Zhou;Lei Li;Xiaofang Zhou","doi":"10.1109/TKDE.2025.3538694","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3538694","url":null,"abstract":"Shortest path computation is ubiquitous in various applications in road networks and the index-based algorithms, especially hub labeling, can boost the query performance dramatically. However, traffic conditions keep changing in real life, making the precomputed index unable to answer the query correctly. In this work, we adopt the state-of-the-art <italic>tree decomposition-based hub labeling (TDHL)</i> as the underlying index and design efficient algorithms to incrementally maintain the index. Specifically, we first analyze the structural stability of the index in dynamic road networks which enables us to concentrate on label value maintenance. We then introduce the <italic>minimum weight property</i> and <italic>minimum distance property</i> to guarantee index correctness without graph traversal. Moreover, we propose the <italic>star-centric paradigm</i> for tracing index change and design various pruning techniques to further accelerate index maintenance. We also extend our algorithms to batch mode for shared computation, to structural maintenance for full types of updates, and generalize to all kinds of <italic>TDHL</i>. Finally, we further improve the index maintenance efficiency and scalability of our algorithms by leveraging graph partition. Our experimental results validate the superiority of our proposals over existing solutions on both index maintenance and query processing.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2784-2801"},"PeriodicalIF":8.9,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769362","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}
Lijie Hu;Xinhai Wang;Yixin Liu;Ninghao Liu;Mengdi Huai;Lichao Sun;Di Wang
{"title":"Towards Stable and Explainable Attention Mechanisms","authors":"Lijie Hu;Xinhai Wang;Yixin Liu;Ninghao Liu;Mengdi Huai;Lichao Sun;Di Wang","doi":"10.1109/TKDE.2025.3538583","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3538583","url":null,"abstract":"Currently, attention mechanism has become a standard fixture in most state-of-the-art natural language processing (NLP) models, not only due to the outstanding performance it could gain but also due to plausible innate explanations for the behaviors of neural architectures it provides, which is notoriously difficult to analyze. However, recent studies show that attention is unstable against randomness and perturbations during training or testing, such as random seeds and slight perturbation of embedding vectors, which impedes it from becoming a faithful explanation tool. Thus, a natural question is whether we can find some substitute for the current attention that is more stable and could keep the most important characteristics of explanation and prediction of attention. In this paper, to resolve the problem, we provide a rigorous definition of such alternate namely SEAT (<u><b>S</b></u>table and <u><b>E</b></u>xplainable <u><b>At</b></u>tention). Specifically, a SEAT should have the following three properties: (1) Its prediction distribution is enforced to be close to the distribution based on the vanilla attention; (2) Its top-<inline-formula><tex-math>$k$</tex-math></inline-formula> indices have large overlaps with those of the vanilla attention; (3) It is robust w.r.t perturbations, i.e., any slight perturbation on SEAT will not change the prediction distribution too much, which implicitly indicates that it is stable to randomness and perturbations. To further improve the interpretability stability against perturbations, based on SEAT we provide another definition called SEAT++. Then we propose a method to get a SEAT++, which could be considered an ad hoc modification for canonical attention. Finally, through intensive experiments on various datasets, we compare our SEAT and SEAT++ with other baseline methods using RNN, BiLSTM, and BERT architectures via six different evaluation metrics for model interpretation, stability, and accuracy. Results show that SEAT and SEAT++ are more stable against different perturbations and randomness while also keeping the explainability of attention, which indicates they provide more faithful explanations. Moreover, compared with vanilla attention, there is almost no utility (accuracy) degradation for SEAT and SEAT++.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"3047-3061"},"PeriodicalIF":8.9,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769564","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}