IEEE Transactions on Knowledge and Data Engineering最新文献

{"title":"HPST-GT: Full-Link Delivery Time Estimation Via Heterogeneous Periodic Spatial-Temporal Graph Transformer","authors":"Shuai Wang;Hai Wang;Li Lin;Xiaohui Zhao;Tian He;Dian Shen;Wei Xi","doi":"10.1109/TKDE.2025.3533610","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3533610","url":null,"abstract":"A warehouse-distribution integration (WDI) e-commerce platform is an approach that combines warehousing and distribution processes, which is increasingly adopted in industry to enhance business efficiency. In the WDI e-commerce, one of the most important problems is to estimate the full-link delivery time for decision-making. Traditional methods designed for separate warehouse-distribution models struggle to address challenges in integrated systems. The difficulties stem from two main factors: (i) the contextual influence exerted by neighboring units within heterogeneous delivery networks, and (ii) the uncertainty in delivery times caused by dynamic and periodic temporal factors such as fluctuations in online sales volumes and the varying characteristics of different delivery units (e.g., warehouses and sorting centers). To address these challenges, we propose a novel full-link delivery time estimation framework called <bold>H</b>eterogeneous <bold>P</b>eriodic <bold>S</b>patial-<bold>T</b>emporal <bold>G</b>raph <bold>T</b>ransformer (<bold>HPST-GT</b>). First, we develop heterogeneous graph transformers to capture the hierarchical and diverse information of the warehouse-distribution network. Next, we design spatial-temporal transformers based on heterogeneous features to analyze the correlation between spatial and temporal information. Finally, we create a heterogeneous spatial-temporal graph prediction module to estimate full-link delivery time. Our method, evaluated on a one-month dataset from a leading e-commerce platform, surpasses current benchmarks across multiple performance metrics.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 4","pages":"1885-1901"},"PeriodicalIF":8.9,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570825","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":"Generating $k$kk-Hop-Constrained $s$ss-$t$tt Path Graphs","authors":"Yuzheng Cai;Siyuan Liu;Weiguo Zheng;Xuemin Lin;Chengbo Zhang;Xuecang Zhang","doi":"10.1109/TKDE.2025.3532318","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3532318","url":null,"abstract":"In this paper, we study two different problems that investigate relations between given vertices <inline-formula><tex-math>$s$</tex-math></inline-formula> and <inline-formula><tex-math>$t$</tex-math></inline-formula>. The first problem is to generate the <inline-formula><tex-math>$k$</tex-math></inline-formula>-hop-constrained <inline-formula><tex-math>$s$</tex-math></inline-formula>-<inline-formula><tex-math>$t$</tex-math></inline-formula> path graph, i.e., the subgraph consisting of all paths from <inline-formula><tex-math>$s$</tex-math></inline-formula> to <inline-formula><tex-math>$t$</tex-math></inline-formula>, where each path is not longer than <inline-formula><tex-math>$k$</tex-math></inline-formula> s.t. <inline-formula><tex-math>$s$</tex-math></inline-formula> and <inline-formula><tex-math>$t$</tex-math></inline-formula> appear only once. To solve the first problem, we propose the <i>A-BiBFS<inline-formula><tex-math>$^{++}$</tex-math><alternatives><mml:math><mml:mi>t</mml:mi></mml:math><inline-graphic></alternatives><alternatives><mml:math><mml:msup><mml:mrow/><mml:mrow><mml:mo>+</mml:mo><mml:mo>+</mml:mo></mml:mrow></mml:msup></mml:math><inline-graphic></alternatives></inline-formula></i> method enhanced with the reduced neighbor index and an approximate vertex grouping strategy. The second problem is to generate the <inline-formula><tex-math>$k$</tex-math></inline-formula>-hop-constrained <inline-formula><tex-math>$s$</tex-math></inline-formula>-<inline-formula><tex-math>$t$</tex-math></inline-formula> simple path graph, i.e., the subgraph consisting of all <inline-formula><tex-math>$k$</tex-math></inline-formula>-hop-constrained simple paths from <inline-formula><tex-math>$s$</tex-math></inline-formula> to <inline-formula><tex-math>$t$</tex-math></inline-formula>, which is proved to be NP-hard on directed graphs. Based on <i>A-BiBFS<inline-formula><tex-math>$^{++}$</tex-math><alternatives><mml:math><mml:mi>t</mml:mi></mml:math><inline-graphic></alternatives><alternatives><mml:math><mml:msup><mml:mrow/><mml:mrow><mml:mo>+</mml:mo><mml:mo>+</mml:mo></mml:mrow></mml:msup></mml:math><inline-graphic></alternatives></inline-formula></i>, we propose the <i>EVE</i> method to tackle the second problem, which exploits the paradigm of edge-wise examination rather than exhaustively enumerating all simple paths. Extensive experiments show that both <i>A-BiBFS<inline-formula><tex-math>$^{++}$</tex-math><alternatives><mml:math><mml:mi>s</mml:mi></mml:math><inline-graphic></alternatives><alternatives><mml:math><mml:msup><mml:mrow/><mml:mrow><mml:mo>+</mml:mo><mml:mo>+</mml:mo></mml:mrow></mml:msup></mml:math><inline-graphic></alternatives></inline-formula></i> and <i>EVE</i> significantly outperform all baselines. Moreover, by taking <i>EVE</i> as a built-in block, state-of-the-art for hop-constrained simple path enumeration can be accelerated by up to an order of magnitude.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2584-2599"},"PeriodicalIF":8.9,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769449","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 Learning in Imbalanced Data Streams With Unpredictable Feature Evolution","authors":"Jiahang Tu;Xijia Tang;Shilin Gu;Yucong Dai;Ruidong Fan;Chenping Hou","doi":"10.1109/TKDE.2025.3531431","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3531431","url":null,"abstract":"Learning from data streams collected sequentially over time are widely spread in real-world applications. Previous methods typically assume that the data stream has a feature space with a fixed or clearly defined evolution pattern, as well as a balanced class distribution. However, in many practical scenarios, such as environmental monitoring systems, the frequency of anomalous events is significantly imbalanced compared to normal ones and the feature space dynamically changes due to ecological evolution and sensor lifespan. To alleviate this important but rarely studied problem, we propose the Adaptive Learning in Imbalace data streams with Unpredictable feature evolution (ALIU) algorithm. As data streams with imbalanced class distribution arrive, ALIU first mitigates the model's bias for the majority class by reweighting the adaptive gradient descent magnitudes between different classes. Then, a new loss function is proposed that simultaneously focuses on misclassifications and maintains model robustness. Further, when imbalanced data streams arrive with feature evolutions, we reuse the previously learned model and update the incomplete and augmented features by adopting the adaptive gradient strategy and ensemble method, respectively. Finally, we utilize the projected technique to build a sparse yet efficient model. Based on a few common and mild assumptions, we theoretically analyze that the ALIU satisfies a sub-linear regret bound under both convex and strong convex loss functions and the performance of model can be improved with the assistance of old features. Besides, extensive experimental results further demonstrate the effectiveness of our proposed algorithm.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 4","pages":"1527-1541"},"PeriodicalIF":8.9,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570799","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":"Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphs","authors":"Pengfei Ding;Yan Wang;Guanfeng Liu;Nan Wang;Xiaofang Zhou","doi":"10.1109/TKDE.2025.3531469","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3531469","url":null,"abstract":"To address the issue of label sparsity in heterogeneous graphs (HGs), heterogeneous graph few-shot learning (HGFL) has recently emerged. HGFL aims to extract meta-knowledge from source HGs with rich-labeled data and transfers it to a target HG, facilitating learning new classes with few-labeled training data and improving predictions on unlabeled testing data. Existing methods typically assume the same distribution across the source HG, training data, and testing data. However, in practice, distribution shifts in HGFL are inevitable due to (1) the scarcity of source HGs that match the target HG's distribution, and (2) the unpredictable data generation mechanism of the target HG. Such distribution shifts can degrade the performance of existing methods, leading to a novel problem of out-of-distribution (OOD) generalization in HGFL. To address this challenging problem, we propose COHF, a <underline>C</u>ausal <underline>O</u>OD <underline>H</u>eterogeneous graph <underline>F</u>ew-shot learning model. In COHF, we first adopt a bottom-up data generative perspective to identify the invariance principle for OOD generalization. Then, based on this principle, we design a novel variational autoencoder-based heterogeneous graph neural network (VAE-HGNN) to mitigate the impact of distribution shifts. Finally, we propose a novel meta-learning framework that incorporates VAE-HGNN to effectively transfer meta-knowledge in OOD environments. Extensive experiments on seven real-world datasets have demonstrated the superior performance of COHF over the state-of-the-art methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 4","pages":"1804-1818"},"PeriodicalIF":8.9,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570795","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":"Enhancing Hyperedge Prediction With Context-Aware Self-Supervised Learning","authors":"Yunyong Ko;Hanghang Tong;Sang-Wook Kim","doi":"10.1109/TKDE.2025.3532263","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3532263","url":null,"abstract":"Hypergraphs can naturally model <i>group-wise relations</i> (e.g., a group of users who co-purchase an item) as <i>hyperedges</i>. <i>Hyperedge prediction</i> is to predict future or unobserved hyperedges, which is a fundamental task in many real-world applications (e.g., group recommendation). Despite the recent breakthrough of hyperedge prediction methods, the following challenges have been rarely studied: (<b>C1</b>) <i>How to aggregate the nodes in each hyperedge candidate for accurate hyperedge prediction?</i> and (<b>C2</b>) <i>How to mitigate the inherent data sparsity problem in hyperedge prediction?</i> To tackle both challenges together, in this paper, we propose a novel hyperedge prediction framework (<b><inline-formula><tex-math>$mathsf{CASH}$</tex-math><alternatives><mml:math><mml:mi>CASH</mml:mi></mml:math><inline-graphic></alternatives></inline-formula></b>) that employs (1) <i>context-aware node aggregation</i> to precisely capture complex relations among nodes in each hyperedge for (C1) and (2) <i>self-supervised contrastive learning</i> in the context of hyperedge prediction to enhance hypergraph representations for (C2). Furthermore, as for (C2), we propose a <i>hyperedge-aware augmentation</i> method to fully exploit the latent semantics behind the original hypergraph and consider both node-level and group-level contrasts (i.e., <i>dual contrasts</i>) for better node and hyperedge representations. Extensive experiments on six real-world hypergraphs reveal that <inline-formula><tex-math>$mathsf{CASH}$</tex-math></inline-formula> consistently outperforms all competing methods in terms of the accuracy in hyperedge prediction and each of the proposed strategies is effective in improving the model accuracy of <inline-formula><tex-math>$mathsf{CASH}$</tex-math></inline-formula>.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 4","pages":"1772-1784"},"PeriodicalIF":8.9,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570614","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":"HyCubE: Efficient Knowledge Hypergraph 3D Circular Convolutional Embedding","authors":"Zhao Li;Xin Wang;Jun Zhao;Wenbin Guo;Jianxin Li","doi":"10.1109/TKDE.2025.3531372","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3531372","url":null,"abstract":"Knowledge hypergraph embedding models are usually computationally expensive due to the inherent complex semantic information. However, existing works mainly focus on improving the effectiveness of knowledge hypergraph embedding, making the model architecture more complex and redundant. It is desirable and challenging for knowledge hypergraph embedding to reach a trade-off between model effectiveness and efficiency. In this paper, we propose an end-to-end efficient knowledge hypergraph embedding model, HyCubE, which designs a novel <i>3D circular convolutional neural network</i> and the <i>alternate mask stack</i> strategy to enhance the interaction and extraction of feature information comprehensively. Furthermore, our proposed model achieves a better trade-off between effectiveness and efficiency by adaptively adjusting the 3D circular convolutional layer structure to handle <inline-formula><tex-math>$n$</tex-math></inline-formula>-ary knowledge tuples of different arities with fewer parameters. In addition, we use a knowledge hypergraph 1-N multilinear scoring way to accelerate the model training efficiency further. Finally, extensive experimental results on all datasets demonstrate that our proposed model consistently outperforms state-of-the-art baselines, with an average improvement of 8.22% and a maximum improvement of 33.82% across all metrics. Meanwhile, HyCubE is 6.12x faster, GPU memory usage is 52.67% lower, and the number of parameters is reduced by 85.21% compared with the average metric of the latest state-of-the-art baselines.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 4","pages":"1902-1914"},"PeriodicalIF":8.9,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570808","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":"AISFuser: Encoding Maritime Graphical Representations With Temporal Attribute Modeling for Vessel Trajectory Prediction","authors":"Zhiwen Zhang;Wei Yuan;Zipei Fan;Xuan Song;Ryosuke Shibasaki","doi":"10.1109/TKDE.2025.3531770","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3531770","url":null,"abstract":"Maritime transportation, vital for nearly 90% of global trade, necessitates precise vessel trajectory prediction for safety and efficiency. Although the Automatic Identification System (AIS) provides a comprehensive data source, how to model these multi-modal and heterogeneous time-varying sequences (such as vessels’ kinetic information and ocean weather factors) poses a formidable challenge. Moreover, most existing approaches are limited by the confined scope of vessel trajectory modeling, making it impossible to consider the unique characteristics of maritime transportation system. To tackle these challenges, we propose a novel framework called AISFuser to i) encode unique maritime traffic network into graphical representations, and ii) introduce the heterogeneity into multi-modal temporal embeddings through Self-Supervised Learning (SSL). Specifically, our AISFuser is constructed by combining an attention-based graph block with a transformer network to encode information across space and time, respectively. In terms of temporal dimension, one SSL auxiliary task is also designed to enhance the heterogeneity of temporal representations and supplement the main vessel prediction task. We validate the effectiveness of the proposed AISFuser on a real-world AIS dataset. Extensive experimental results demonstrate that our method can forecast multiple attributes of vessel trajectory for over 10 hours into the future, outperforming competitive baselines.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 4","pages":"1571-1584"},"PeriodicalIF":8.9,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570826","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":"AEGK: Aligned Entropic Graph Kernels Through Continuous-Time Quantum Walks","authors":"Lu Bai;Lixin Cui;Ming Li;Peng Ren;Yue Wang;Lichi Zhang;Philip S. Yu;Edwin R. Hancock","doi":"10.1109/TKDE.2024.3512181","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3512181","url":null,"abstract":"In this work, we develop a family of Aligned Entropic Graph Kernels (AEGK) for graph classification. We commence by performing the Continuous-time Quantum Walk (CTQW) on each graph structure, and compute the Averaged Mixing Matrix (AMM) to describe how the CTQW visits all vertices from a starting vertex. More specifically, we show how this AMM matrix allows us to compute a quantum Shannon entropy of each vertex for either un-attributed or attributed graphs. For pairwise graphs, the proposed AEGK kernels are defined by computing the kernel-based similarity between the quantum Shannon entropies of their pairwise aligned vertices. The analysis of theoretical properties reveals that the proposed AEGK kernels cannot only address the shortcoming of neglecting the structural correspondence information between graphs arising in most existing R-convolution graph kernels, but also overcome the problems of neglecting the structural differences and vertex-attributed information arising in existing vertex-based matching kernels. Moreover, unlike most existing classical graph kernels that only focus on the global or local structural information of graphs, the proposed AEGK kernels can simultaneously capture both global and local structural characteristics through the quantum Shannon entropies, reflecting more precise kernel-based similarity measures between pairwise graphs. The above theoretical properties explain the effectiveness of the proposed AEGK kernels. Experimental evaluations demonstrate that the proposed kernels can outperform state-of-the-art graph kernels and deep learning models for graph classification.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1064-1078"},"PeriodicalIF":8.9,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106843","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":"Data Optimization in Deep Learning: A Survey","authors":"Ou Wu;Rujing Yao","doi":"10.1109/TKDE.2025.3530916","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3530916","url":null,"abstract":"Large-scale, high-quality data are considered an essential factor for the successful application of many deep learning techniques. Meanwhile, numerous real-world deep learning tasks still have to contend with the lack of sufficient amounts of high-quality data. Additionally, issues such as model robustness, fairness, and trustworthiness are also closely related to training data. Consequently, a huge number of studies in the existing literature have focused on the data aspect in deep learning tasks. Some typical data optimization techniques include data augmentation, logit perturbation, sample weighting, and data condensation. These techniques usually come from different deep learning divisions and their theoretical inspirations or heuristic motivations may seem unrelated to each other. This study aims to organize a wide range of existing data optimization methodologies for deep learning from the previous literature, and makes the effort to construct a comprehensive taxonomy for them. The constructed taxonomy considers the diversity of split dimensions, and deep sub-taxonomies are constructed for each dimension. On the basis of the taxonomy, connections among the extensive data optimization methods for deep learning are built in terms of five aspects. We probe into rendering several promising and interesting future directions. The constructed taxonomy and the revealed connections will enlighten the better understanding of existing methods and the design of novel data optimization techniques. Furthermore, our aspiration for this survey is to promote data optimization as an independent subdivision of deep learning.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2356-2375"},"PeriodicalIF":8.9,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769513","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":"Mitigating the Tail Effect in Fraud Detection by Community Enhanced Multi-Relation Graph Neural Networks","authors":"Li Han;Longxun Wang;Ziyang Cheng;Bo Wang;Guang Yang;Dawei Cheng;Xuemin Lin","doi":"10.1109/TKDE.2025.3530467","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3530467","url":null,"abstract":"Fraud detection, a classical data mining problem in finance applications, has risen in significance amid the intensifying confrontation between fraudsters and anti-fraud forces. Recently, an increasing number of criminals are constantly expanding the scope of fraud activities to covet the property of innocent victims. However, most existing approaches require abundant historical records to mine fraud patterns from financial transaction behaviors, thereby leading to significant challenges to protect minority groups, who are less involved in the modern financial market but also under the threat of fraudsters nowadays. Therefore, in this paper, we propose a novel community-enhanced multi-relation graph neural network-based model, named CMR-GNN, to address the important defects of existing fraud detection models in the tail effect situation. In particular, we first construct multiple types of relation graphs from historical transactions and then devise a clustering-based neural network module to capture diverse patterns from transaction communities. To mitigate information lacking tailed nodes, we proposed tailed-groups learning modules to aggregate features from similarly clustered subgraphs by graph convolution networks. Extensive experiments on both the real-world and public datasets demonstrate that our method not only surpasses the state-of-the-art baselines but also could effectively harness information within transaction communities while mitigating the impact of tail effects.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 4","pages":"2029-2041"},"PeriodicalIF":8.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570593","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}