{"title":"CGoFed: Constrained Gradient Optimization Strategy for Federated Class Incremental Learning","authors":"Jiyuan Feng;Xu Yang;Liwen Liang;Weihong Han;Binxing Fang;Qing Liao","doi":"10.1109/TKDE.2025.3544605","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3544605","url":null,"abstract":"Federated Class Incremental Learning (FCIL) has emerged as a new paradigm due to its applicability in real-world scenarios. In FCIL, clients continuously generate new data with unseen class labels and do not share local data due to privacy restrictions, and each client’s class distribution evolves dynamically and independently. However, existing work still faces two significant challenges. Firstly, current methods lack a better balance between maintaining sound anti-forgetting effects over old data (stability) and ensuring good adaptability for new tasks (plasticity). Secondly, some FCIL methods overlook that the incremental data will also have a non-identical label distribution, leading to poor performance. This paper proposes CGoFed, which includes relax-constrained gradient update and cross-task gradient regularization modules. The relax-constrained gradient update prevents forgetting the knowledge about old data while quickly adapting to the new data by constraining the gradient update direction to a gradient space that minimizes interference with historical tasks. The cross-task gradient regularization also finds applicable historical models from other clients and trains a personalized global model to address the non-identical label distribution problem. The results demonstrate that the CGoFed performs well in alleviating catastrophic forgetting and improves model performance by 8% -23% compared with the SOTA comparison method.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2282-2295"},"PeriodicalIF":8.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769460","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":"MTD-DS: An SLA-Aware Decision Support Benchmark for Multi-Tenant Parallel DBMSs","authors":"Shaoyi Yin;Franck Morvan;Jorge Martinez-Gil;Abdelkader Hameurlain","doi":"10.1109/TKDE.2025.3543727","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543727","url":null,"abstract":"Multi-tenant DBMSs are used by cloud providers for their Database-as-a-Service products. They could be single-node DBMSs installed in virtual machines, SQL-on-Hadoop systems or classic parallel relational DBMSs running on top of a shared-nothing or shared-disk architecture. For a cloud provider, it is interesting to measure these systems’ capability of dealing with multi-tenant workloads, i.e., taking advantage of the statistical multiplexing to obtain economic gain while being attractive by providing a good quality of service and a low bill to the tenants. In this paper, we present MTD-DS benchmark (with MTD for Multi-Tenant parallel DBMSs and DS for Decision Support). MTD-DS extends TPC-DS by adding a multi-tenant query workload generator, a performance Service Level Objectives generator, configurable Database-as-a-Service pricing models, and new metrics to measure the potential capability of a multi-tenant parallel DBMS in obtaining the best trade-off between the provider's benefit and the tenants’ satisfaction. Example experimental results have been produced to show the relevance and the feasibility of the MTD-DS benchmark.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2743-2755"},"PeriodicalIF":8.9,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769459","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}
Haoran Tang;Shiqing Wu;Zhihong Cui;Yicong Li;Guandong Xu;Qing Li
{"title":"Model-Agnostic Dual-Side Online Fairness Learning for Dynamic Recommendation","authors":"Haoran Tang;Shiqing Wu;Zhihong Cui;Yicong Li;Guandong Xu;Qing Li","doi":"10.1109/TKDE.2025.3544510","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3544510","url":null,"abstract":"Fairness in recommendation has drawn much attention since it significantly affects how users access information and how information is exposed to users. However, most fairness-aware methods are designed offline with the entire stationary interaction data to handle the global unfairness issue and evaluate their performance in a one-time paradigm. In real-world scenarios, users tend to interact with items continuously over time, leading to a dynamic recommendation environment where unfairness is evolving online. Moreover, previous methods that focus on mitigating the unfairness can hardly bring significant improvements to the recommendation task. Hence, in this paper, we propose a <bold><u>M</u></b>odel-agnostic <bold><u>D</u></b>ual-side <bold><u>O</u></b>nline <bold><u>Fair</u></b>ness Learning method (MDOFair) for the dynamic recommendation. First, we carefully design dynamic dual-side fairness learning to trace the rapid evolution of unfairness from both the user and item sides. Second, we leverage the fairness and recommendation tasks in one utilized framework to pursue the double-win success. Last, we present an efficient model-agnostic post-ranking method for the dynamic recommendation scenario to mitigate the dynamic unfairness while improving the recommendation performance significantly. Extensive experiments demonstrate the superiority and effectiveness of our proposed MDOFair by incorporating it into existing dynamic models as a post-ranking stage.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2727-2742"},"PeriodicalIF":8.9,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769370","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":"Efficient PMU Data Compression Using Enhanced Graph Filtering Enabled Principal Component Analysis","authors":"Manish Pandit;Ranjana Sodhi","doi":"10.1109/TKDE.2025.3544768","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3544768","url":null,"abstract":"Phasor Measurement Units (PMUs) are state-of-the-art measuring devices that capture high-resolution time-synchronized voltage and current phasor measurements in wide area monitoring systems (WAMS). Their usage for various real-time applications demands a huge amount of data collected from multiple PMUs to be transmitted from the local phasor data concentrator (PDC) to the control centre. To optimize the requirements of bandwidth to transmit the data as well as to store the data, an efficient synchrophasor data compression technique is desired. To this end, this paper presents a 3-stage data compression scheme in which Stage-1 performs the accumulation of the data matrix from the optimally placed PMUs in WAMS into the local PDC. The data is then passed through a novel Ramanujan's sum-based fault window detection algorithm to identify the fault within the PMU data matrix in Stage-2. Finally, Stage-3 proposes an enhanced graph filtering-enabled principal component analysis scheme which expands the notion of conventional PCA techniques into the graph domain to compress the data. The performance of the proposed scheme is verified on the IEEE 14-bus system and New England 39-bus system. Further, practical applicability of the proposed method is validated on field PMU data collected from EPFL campus in Switzerland.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2488-2500"},"PeriodicalIF":8.9,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769537","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":"Transfer-and-Fusion: Integrated Link Prediction Across Knowledge Graphs","authors":"Yuanning Cui;Zequn Sun;Wei Hu","doi":"10.1109/TKDE.2025.3544255","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3544255","url":null,"abstract":"Existing work on knowledge graph (KG) link prediction has primarily focused on a single KG. However, a single KG is often limited by its incompleteness, encompassing missing facts, entities, and relations. This limitation subsequently restricts the practicality, as it cannot handle the queries that involve missing entities or relations within the single KG. In this article, we explore an extended link prediction task, <italic>cross-KG link prediction</i>, which answers queries using entities or relations integrated from other KGs. The crux of this problem is transferring knowledge across KGs and fusing their embedding spaces, which possess varying schemata. We develop a relation prototype graph to model the interactions among relations from different KGs. Based on this graph, we first propose a dual-view embedding learning module to fuse embedding spaces by training with instance facts and relation prototype edges. We then introduce an attention mechanism to highlight pivotal information for specific queries, recognizing that different KGs often emphasize various domains. Moreover, we devise an augmentation strategy to generate pseudo-cross-KG facts, facilitating knowledge transfer across KGs. Using four widely-used KGs, we construct two cross-KG link prediction datasets. Extensive experimental results demonstrate the superiority of our model and the unique contributions of each module.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"3062-3074"},"PeriodicalIF":8.9,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769393","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 Knowledge Graph Completion With Star and Ring Topology Information Aggregation","authors":"Jing Zhao;Xinzhu Zhang;Yujia Li;Shiliang Sun","doi":"10.1109/TKDE.2025.3544202","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3544202","url":null,"abstract":"Few-shot knowledge graph completion (FKGC) addresses the long-tail problem of relations by leveraging a few observed support entity pairs to infer unknown facts for tail-located relations. Learning the relation representation of entity pairs and evaluating the match of query and support entity pairs are the two key steps of FKGC. Existing methods learn the representation of entity pairs by either aggregating neighbors of entities or integrating relation representations in the connected paths from head to tail. However, in few-shot scenarios, the limited number of support entity pairs and insufficient structural information with a single neighborhood topology will lead to matching failure. To this end, we consider the star and ring topological information for a given entity pair: (1) Entity neighborhood, which captures multi-hop neighbors of entities; (2) Relational path, which characterizes compound relation forms. Furthermore, to effectively fuse the two kinds of heterogeneous topological information, we design the multi-aggregator and the fine-grained path correlation matching algorithm to obtain more delicate and balanced matching. Based on the proposed relational path correlation matching module, we propose the relation adaptive network to solve the few-shot temporal knowledge graph completion problem. The experimental results show that our method continuously outperforms the state-of-the-art methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2525-2537"},"PeriodicalIF":8.9,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769559","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 Attribute-Driven Fraud Detection With Risk-Aware Graph Representation","authors":"Sheng Xiang;Guibin Zhang;Dawei Cheng;Ying Zhang","doi":"10.1109/TKDE.2025.3543887","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543887","url":null,"abstract":"Credit card fraud is a severe issue that causes significant losses for both cardholders and issuing banks. Existing methods utilize machine learning-based classifiers to identify fraudulent transactions from labeled transaction records. However, labeled data are often scarce compared to the billions of real transactions due to the high cost of annotation, which means that previous methods do not fully utilize the rich features of unlabeled data. What’s more, contemporary methods succumb to a fallacy of unawareness of the local risk structure and the inability to capture certain risk patterns. Therefore, we propose the Risk-aware Gated Temporal Attention Network (RGTAN) for fraud detection in this work. Specifically, we first build a temporal transaction graph based on the transaction records, which consists of temporal transactions (nodes) and their interactions (edges). Then we leverage a Gated Temporal Graph Attention (GTGA) Mechanism to propagate messages among the nodes and learn adaptive representations of transactions. We also model the fraud patterns through risk propagation, taking advantage of the relations among transactions. More importantly, we devise a neighbor risk-aware representation learning layer to enhance our method’s perception of multi-hop risk structures. We conduct extensive experiments on a real-world credit card transaction dataset and two public fraud detection datasets. The results show that our proposed method, RGTAN, outperforms other state-of-the-art methods on three fraud detection datasets. The risk-aware semi-supervised experiments also demonstrate the excellent performance of our model with only a small fraction of manually labeled data. Moreover, RGTAN has been deployed in a world-leading credit card issuer for credit card fraud detection, and the case study results show the effectiveness of our method in uncovering real-world fraud patterns.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2501-2512"},"PeriodicalIF":8.9,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769368","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}
Paul Boniol;Donato Tiano;Angela Bonifati;Themis Palpanas
{"title":"-Graph: A Graph Embedding for Interpretable Time Series Clustering","authors":"Paul Boniol;Donato Tiano;Angela Bonifati;Themis Palpanas","doi":"10.1109/TKDE.2025.3543946","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543946","url":null,"abstract":"Time series clustering poses a significant challenge with diverse applications across domains. A prominent drawback of existing solutions lies in their limited interpretability, often confined to presenting users with centroids. In addressing this gap, our work presents <inline-formula><tex-math>$k$</tex-math></inline-formula>-Graph, an unsupervised method explicitly crafted to augment interpretability in time series clustering. Leveraging a graph representation of time series subsequences, <inline-formula><tex-math>$k$</tex-math></inline-formula>-Graph constructs multiple graph representations based on different subsequence lengths. This feature accommodates variable-length time series without requiring users to predetermine subsequence lengths. Our experimental results reveal that <inline-formula><tex-math>$k$</tex-math></inline-formula>-Graph outperforms current state-of-the-art time series clustering algorithms in accuracy, while providing users with meaningful explanations and interpretations of the clustering outcomes.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2680-2694"},"PeriodicalIF":8.9,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769457","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}
Ben Yang;Xuetao Zhang;Jinghan Wu;Feiping Nie;Fei Wang;Badong Chen
{"title":"Scalable Min-Max Multi-View Spectral Clustering","authors":"Ben Yang;Xuetao Zhang;Jinghan Wu;Feiping Nie;Fei Wang;Badong Chen","doi":"10.1109/TKDE.2025.3543817","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543817","url":null,"abstract":"Multi-view spectral clustering has attracted considerable attention since it can explore common geometric structures from diverse views. Nevertheless, existing min-min framework-based models adopt internal minimization to find the view combination with the minimized within-cluster variance, which will lead to effectiveness loss since the real clusters often exhibit high within-cluster variance. To address this issue, we provide a novel scalable min-max multi-view spectral clustering (SMMSC) model to improve clustering performance. Besides, anchor graphs, rather than full sample graphs, are utilized to reduce the computational complexity of graph construction and singular value decomposition, thereby enhancing the applicability of SMMSC to large-scale applications. Then, we rewrite the min-max model as a minimized optimal value function, demonstrate its differentiability, and develop an efficient gradient descent-based algorithm to optimize it with linear computational complexity. Moreover, we demonstrate that the resultant solution of the proposed algorithm is the global optimum. Numerous experiments on different real-world datasets, including some large-scale datasets, demonstrate that SMMSC outperforms existing state-of-the-art multi-view clustering methods regarding clustering performance.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2918-2931"},"PeriodicalIF":8.9,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769539","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":"Probabilistic Learning of Multivariate Time Series With Temporal Irregularity","authors":"Yijun Li;Cheuk Hang Leung;Qi Wu","doi":"10.1109/TKDE.2025.3544348","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3544348","url":null,"abstract":"Probabilistic forecasting of multivariate time series is essential for various downstream tasks. Most existing approaches rely on the sequences being uniformly spaced and aligned across all variables. However, real-world multivariate time series often suffer from temporal irregularities, including nonuniform intervals and misaligned variables, which pose significant challenges for accurate forecasting. To address these challenges, we propose an end-to-end framework that models temporal irregularities while capturing the joint distribution of variables at arbitrary continuous-time points. Specifically, we introduce a dynamic conditional continuous normalizing flow to model data distributions in a non-parametric manner, accommodating the complex, non-Gaussian characteristics commonly found in real-world datasets. Then, by leveraging a carefully factorized log-likelihood objective, our approach captures both temporal and cross-sectional dependencies efficiently. Extensive experiments on a range of real-world datasets demonstrate the superiority and adaptability of our method compared to existing approaches.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2874-2887"},"PeriodicalIF":8.9,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769541","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}