IEEE Transactions on Knowledge and Data Engineering最新文献

{"title":"Local Community Detection in Multi-Attributed Road-Social Networks","authors":"Li Ni;Qiuyu Li;Yiwen Zhang;Wenjian Luo;Victor S. Sheng","doi":"10.1109/TKDE.2025.3550476","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3550476","url":null,"abstract":"The information available in multi-attributed road-social networks includes network structure, location information, and numerical attributes. Most studies mainly focus on mining communities by combining structure with attributes or structure with location, which do not consider structure, attributes, and location simultaneously. Therefore, we propose a parameter-free algorithm, called LCDMRS, to mine local communities in multi-attributed road-social networks. LCDMRS extracts a sub-network surrounding the given node and embeds it to generate the vector representations of nodes, which incorporates both structural and attributed information. Based on the vector representations of nodes, the average cosine similarity between nodes is designed to ensure both the structural and attributed cohesiveness of the community, while the community node density is designed to ensure the spatial cohesiveness of the community. Targeting the community node density and cosine similarity of nodes, LCDMRS takes the given node as the starting node and employs the community dominance relation to expand the community outward. Experimental results on multiple real-world datasets demonstrate LCDMRS outperforms comparison algorithms.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 6","pages":"3514-3527"},"PeriodicalIF":8.9,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896148","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":"Complementary Learning Subnetworks Towards Parameter-Efficient Class-Incremental Learning","authors":"Depeng Li;Zhigang Zeng;Wei Dai;Ponnuthurai Nagaratnam Suganthan","doi":"10.1109/TKDE.2025.3550809","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3550809","url":null,"abstract":"In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. To mitigate the catastrophic forgetting phenomenon, typical CIL methods either cumulatively store exemplars of old classes for retraining model parameters from scratch or progressively expand model size as new classes arrive, which, however, compromises their practical value due to little attention paid to <italic>parameter efficiency</i>. In this paper, we contribute a novel solution, effective control of the parameters of a well-trained model, by the synergy between two complementary learning subnetworks. Specifically, we integrate one plastic feature extractor and one analytical feed-forward classifier into a unified framework amenable to streaming data. In each CIL session, it achieves non-overwritten parameter updates in a cost-effective manner, neither revisiting old task data nor extending previously learned networks; Instead, it accommodates new tasks by attaching a tiny set of declarative parameters to its backbone, in which only one matrix per task or one vector per class is kept for knowledge retention. Experimental results on a variety of task sequences demonstrate that our method achieves competitive results against state-of-the-art CIL approaches, especially in accuracy gain, knowledge transfer, training efficiency, and task-order robustness. Furthermore, a graceful forgetting implementation on previously learned trivial tasks is empirically investigated to make its non-growing backbone (i.e., a model with limited network capacity) suffice to train on more incoming tasks.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 6","pages":"3240-3252"},"PeriodicalIF":8.9,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896139","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":"RayE-Sub: Countering Subgraph Degradation via Perfect Reconstruction","authors":"Kuo Yang;Zhengyang Zhou;Xu Wang;Pengkun Wang;Limin Li;Yang Wang","doi":"10.1109/TKDE.2025.3544696","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3544696","url":null,"abstract":"Subgraph learning has dominated most practices of improving the expressive power of Message Passing Neural Networks (MPNNs). Existing subgraph discovery policies can be classified into node-based and partition-based, which both achieve impressive performance in most scenarios. However, both mainstream solutions still face a subgraph degradation trap. Subgraph degradation is reflected in the phenomenon that the subgraph-level methods fail to offer any benefits over node-level MPNNs. In this work, we empirically investigate the existence of the subgraph degradation issue and introduce a unified perspective, perfect reconstruction, to provide insights for improving two lines of methods. We further propose a subgraph learning strategy guided by the principle of perfect reconstruction. To achieve this, two major issues should be well-addressed, i.e., <italic>(i) how to ensure the subgraphs to possess with ‘perfect’ information? (ii) how to guarantee the ‘reconstruction’ power of obtained subgraphs?</i> First, we propose a subgraph partition strategy <italic>Rayleigh-resistance</i> to extract non-overlap subgraphs by leveraging the graph spectral theory. Second, we put forward a <italic>Query</i> mechanism to achieve subgraph-level equivariant learning, which guarantees subgraph reconstruction ability. These two parts, <italic>perfect subgraph partition</i> and <italic>equivariant subgraph learning</i> are seamlessly unified as a novel <italic><u>Ray</u>leigh-resistance <u>E</u>quivariant <u>Sub</u>graph learning</i> architecture (<italic><b>RayE-Sub</b></i>). Comprehensive experiments on both synthetic and real datasets demonstrate that our approach can consistently outperform previous subgraph learning architectures.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 6","pages":"3684-3699"},"PeriodicalIF":8.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896435","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":"Disentangling Inter- and Intra-Cascades Dynamics for Information Diffusion Prediction","authors":"Zhangtao Cheng;Yang Liu;Ting Zhong;Kunpeng Zhang;Fan Zhou;Philip S. Yu","doi":"10.1109/TKDE.2025.3568289","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3568289","url":null,"abstract":"Information diffusion prediction is a vital component for a wide range of social applications, including viral marketing identification and precise recommendation. Prior methods focus on modeling contextual information from a single cascade, ignoring rich collaborative information behind historical interactions across various cascades and future data within the cascade. Leveraging such interactions can substantially enhance diffusion prediction performance but presents two major challenges: (1) user intents are usually entangled behind historical interactions; and (2) utilizing future data may introduce severe training-inference discrepancies. We present MIM, a novel information diffusion model merging multi-scale interactions for improving user intent learning and behavior retrieval. Specifically, we convert cascades and social relations into multi-channel hypergraphs, where each channel depicts a common fine-grained user intent behind historical interactions across cascades. By aggregating embeddings learned through multiple channels, we obtain comprehensive intent representations. Second, we decouple past- and future-level temporal influences within a cascade via a dual temporal network. Then we implement past-future knowledge transferring to enhance the knowledge learned from the dual network via hierarchical knowledge distillation. Extensive experiments conducted on four datasets demonstrate that MIM significantly outperforms various benchmarks.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 8","pages":"4548-4563"},"PeriodicalIF":8.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572997","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":"Top-K Representative Search for Comparative Tree Summarization","authors":"Yuqi Chen;Xin Huang;Bilian Chen","doi":"10.1109/TKDE.2025.3565845","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3565845","url":null,"abstract":"Data summarization aims at utilizing a small-scale summary to represent massive datasets as a whole, which is useful for visualization and information sipped generation. However, most existing studies of hierarchical summarization only work on <i>one single tree</i> by selecting <inline-formula><tex-math>$k$</tex-math></inline-formula> representative nodes, which neglects an important problem of comparative summarization on two trees. In this paper, given two trees with the same topology structure and different node weights, we aim at finding <inline-formula><tex-math>$k$</tex-math></inline-formula> representative nodes, where <inline-formula><tex-math>$k_{1}$</tex-math></inline-formula> nodes summarize the common relationship between them and <inline-formula><tex-math>$k_{2}$</tex-math></inline-formula> nodes highlight significantly different subtrees meanwhile satisfying <inline-formula><tex-math>$k_{1}+k_{2}=k$</tex-math></inline-formula>. To optimize summarization results, we introduce a scaling coefficient for balancing the summary view between two subtrees in terms of similarity and difference. Additionally, we propose a novel definition based on the Hellinger distance to quantify the node distribution difference between two subtrees. We present a greedy algorithm SVDT to find high-quality results with approximation guaranteed in an efficient way. Furthermore, we explore an extension of our comparative summarization to handle two trees with different structures. Extensive experiments demonstrate the effectiveness and efficiency of our SVDT algorithm against existing summarization competitors.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 8","pages":"4873-4879"},"PeriodicalIF":8.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10998939","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hypergraph Convolutional Networks for Course Recommendation in MOOCs","authors":"Zhu Su;Yafeng Li;Qing Li;Zhonghua Yan;Longfeng Zhao;Zhi Liu;Jianwen Sun;Sannyuya Liu","doi":"10.1109/TKDE.2025.3568709","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3568709","url":null,"abstract":"Mining learner preferences and needs from individual learning behavior data is a critical task in course recommendation systems. While graph-based models have shown efficacy in capturing pairwise relationships between learners and courses, they often overlook the complex higher-order interactions involving learners, courses and teachers that are essential for accurate recommendations. To address this limitation, we propose a novel Hypergraph Convolutional Network for Course Recommendation (HCNCR) framework, designed to model these higher-order interactions effectively. Our approach constructs course and learner hypergraphs based on course attributes and learner similarity relations, respectively. By employing hypergraph convolution, we capture the intrinsic higher-order relationships within these hypergraphs. Additionally, we utilize graph convolutional layers on the learner-course bipartite graph to integrate embeddings derived from hypergraphs, achieving comprehensive representations of both learners and courses. Extensive experiments conducted on real-world datasets demonstrate that HCNCR significantly outperforms existing state-of-the-art methods in course recommendation tasks.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 8","pages":"4691-4703"},"PeriodicalIF":8.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144573007","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":"A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective","authors":"Ziwen Zhao;Yixin Su;Yuhua Li;Yixiong Zou;Ruixuan Li;Rui Zhang","doi":"10.1109/TKDE.2025.3568147","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3568147","url":null,"abstract":"The field of graph foundation models (GFMs) has seen a dramatic rise in interest in recent years. Their powerful generalization ability is believed to be endowed by self-supervised pre-training and downstream tuning techniques. There is a wide variety of knowledge patterns embedded in the graph data, such as node properties and clusters, which are crucial for learning generalized representations for GFMs. We present a comprehensive survey of self-supervised GFMs from a novel knowledge-based perspective. Our main contribution is a knowledge-based taxonomy that categorizes self-supervised graph models by the specific graph knowledge utilized: microscopic (nodes, links, etc.), mesoscopic (context, clusters, etc.), and macroscopic (global structure, manifolds, etc.). It covers a total of 9 knowledge categories and 300 references for self-supervised pre-training as well as various downstream tuning strategies. Such a knowledge-based taxonomy allows us to more clearly re-examine potential GFM architectures, including large language models (LLMs), as well as provide deeper insights for constructing future GFMs.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 8","pages":"4389-4410"},"PeriodicalIF":8.9,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144573017","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":"Pattern-Wise Transparent Sequential Recommendation","authors":"Kun Ma;Cong Xu;Zeyuan Chen;Wei Zhang","doi":"10.1109/TKDE.2025.3549032","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3549032","url":null,"abstract":"A transparent decision-making process is essential for developing reliable and trustworthy recommender systems. For sequential recommendation, it means that the model can identify key items that account for its recommendation results. However, achieving both interpretability and recommendation performance simultaneously is challenging, especially for models that take the entire sequence of items as input without screening. In this paper, we propose an interpretable framework (named PTSR) that enables a pattern-wise transparent decision-making process without extra features. It breaks the sequence of items into multi-level patterns that serve as atomic units throughout the recommendation process. The contribution of each pattern to the outcome is quantified in the probability space. With a carefully designed score correction mechanism, the pattern contribution can be implicitly learned in the absence of ground-truth key patterns. The final recommended items are those that most key patterns strongly endorse. Extensive experiments on five public datasets demonstrate remarkable recommendation performance, while statistical analysis and case studies validate the model interpretability.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 6","pages":"3627-3640"},"PeriodicalIF":8.9,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896278","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":"Robust Tensor Completion With Side Information","authors":"Yao Wang;Qianxin Yi;Yiyang Yang;Shanxing Gao;Shaojie Tang;Di Wang","doi":"10.1109/TKDE.2025.3566441","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3566441","url":null,"abstract":"Although robust tensor completion has been extensively studied, the effect of incorporating side information has not been explored. In this article, we fill this gap by developing a novel high-order robust tensor completion model that incorporates both latent and explicit side information. We base our model on the transformed t-product because the corresponding tensor tubal rank can characterize the inherent low-rank structure of a tensor. We study the effect of side information on sample complexity and prove that our model needs fewer observations than other tensor recovery methods when side information is perfect. This theoretically shows that informative side information is beneficial for learning. Extensive experimental results on synthetic and real data further demonstrate the superiority of the proposed method over several popular alternatives. In particular, we evaluate the performance of our solution based on two important applications, namely, link prediction in signed networks and rating prediction in recommender systems. We show that the proposed model, which manages to exploit side information in learning, outperforms other methods in the learning of such low-rank tensor data. Furthermore, when dealing with varying dimensions, we also design an online robust tensor completion with side information algorithm and validate its effectiveness using a real-world traffic dataset in the supplementary material.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 8","pages":"4805-4819"},"PeriodicalIF":8.9,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144573011","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":"Generalized Local Prominence for Source Detection in Real-World Rumor Networks","authors":"Syed Shafat Ali;Ajay Rastogi;Tarique Anwar;Syed Afzal Murtaza Rizvi;Jian Yang;Jia Wu;Quan Z. Sheng","doi":"10.1109/TKDE.2025.3567282","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3567282","url":null,"abstract":"The problem of infection source detection deals with localizing the infection source in a given network. While the problem has been extensively studied in the past, researchers have mainly focused on simulated infection networks which may not be the correct reflection of the dynamics of real-world infections. More significantly, the existing methods assume that a rumor source lies at the center of an infection network (source-centrality), which is not always true in sparse real-world rumor networks. Due to the randomness of infection flow in such networks, the source may lie away from the center (source-skewness). There is also a lack of real-world infection network datasets to provide a true real-world perspective. Therefore, we revisit the source detection problem and contemplate a shift from mainstream simulations to a real-world paradigm. To this end, we generate two novel rumor network datasets, <inline-formula><tex-math>${mathsf {Cov19-RN}}$</tex-math></inline-formula> and <inline-formula><tex-math>${mathsf {Use20-RN}}$</tex-math></inline-formula>, based on COVID-19 and US Elections 2020 misinformation trends on Twitter (currently <inline-formula><tex-math>$mathbb {X}$</tex-math></inline-formula>). Besides, inspired by the technicalities inherent to real-world rumor networks, we propose a real-world oriented algorithm called Generalized Exoneration and Prominence based Age, <inline-formula><tex-math>${mathsf {GEPA}}$</tex-math></inline-formula>, for rumor source detection. <inline-formula><tex-math>${mathsf {GEPA}}$</tex-math></inline-formula> addresses the problem of source-skewness to detect rumor sources using the concept of generalized local prominence, which we introduce in this study. Our experiments show that <inline-formula><tex-math>${mathsf {GEPA}}$</tex-math></inline-formula> significantly outperforms the state-of-the-art methods, producing detection rates of 73.6% against 61.5% of the closest competing method on <inline-formula><tex-math>${mathsf {Cov19-RN}}$</tex-math></inline-formula>, and 61.5% against 52.6% of the closest competing method on <inline-formula><tex-math>${mathsf {Use20-RN}}$</tex-math></inline-formula>. To the best of our knowledge, this study is the first such work to deal with source detection in real-world rumor networks and address the problem of source-skewness.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 8","pages":"4620-4634"},"PeriodicalIF":8.9,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572995","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}