IEEE Transactions on Knowledge and Data Engineering最新文献

{"title":"HGOOD-D: Hyperbolic Hierarchical Exploration for Graph Out-of-Distribution Detection","authors":"Yuntai Ding;Tao Ren;Yiwei Fu;Yifan Wang;Haodong Zhang;Chong Chen;Wei Ju;Xiao Luo;Xian-Sheng Hua","doi":"10.1109/TKDE.2026.3690579","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3690579","url":null,"abstract":"Out-of-distribution (OOD) detection has garnered increasing concern for identifying test samples that exhibit a distributional shift from the training dataset in practical deep learning applications. With the significant advancements in graph deep learning for graph representation, graph OOD detection has emerged as a research problem. Graph contrastive learning (GCL) is applied to graph OOD detection due to its capacity for learning discriminative representations in a self-supervised manner, thereby eliminating the need for time-consuming and labor-intensive label information. However, existing methods often neglect the explicit consideration of underlying semantics behind graph data distribution for OOD detection. We observe that naive data augmentations in GCL may inadvertently compromise the intrinsic graph structure while retaining redundant structural information, which hinders semantic discrimination between graphs. Additionally, euclidean space embedding struggles to maintain hierarchical structural consistency, making it challenging to meaningfully capture the hierarchical semantic distribution of graph data. In response to these issues, we propose a novel framework termed HGOOD-D, which aims to explore latent semantic hierarchies in hyperbolic space for graph OOD detection. Specifically, we design a bottleneck graph extractor grounded in the information bottleneck (IB) principle, which captures the minimal sufficient information to distinguish graph patterns. Based on this, we introduce hierarchical contrastive learning to capture the hierarchical semantics within graph data distribution. These methods are based on hyperbolic space embedding that can preserve complex inter-relationships in graph hierarchies, thereby mitigating data distortion. Comprehensive evaluations on ten widely used benchmark datasets show that HGOOD-D consistently surpasses current state-of-the-art approaches in graph OOD detection.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4405-4418"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148507532","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":"Furion: Efficient and Atomic Cross-Blockchain Transactions Through Multi-Future Exploration","authors":"Ru Cheng;Yifan Zhou;Jiang Xiao;Shijie Zhang;Haoyu Dong;Hai Jin;Bo Li","doi":"10.1109/TKDE.2026.3684675","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3684675","url":null,"abstract":"Cross-chain transaction processing is pivotal to blockchain interoperability, enabling coordinated state transitions across multiple blockchains to support increasingly complex <italic>decentralized applications</i> (dApps). However, existing atomicity-preserving mechanisms, predominantly based on <italic>two-phase commit</i> (2 PC) protocols, are hindered by sequential coordination, prolonged state locking, and high susceptibility to cascading aborts. These limitations severely degrade throughput and latency under contention, undermining practical deployability. This paper proposes Furion, a novel cross-chain transaction processing mechanism that achieves both atomicity and efficiency. Furion introduces the multi-future exploration, a new execution paradigm that explicitly materializes multiple possible futures of cross-chain states via multi-versioning. By speculatively executing transactions across feasible state evolutions, Furion eliminates blocking on unresolved dependencies and fundamentally avoids cascading aborts. To further unlock concurrency in the finalization phase, Furion employs preemptive voting, which allows local transactions to cast commit or abort votes early when their outcomes are invariant across all state versions. Experimental evaluations demonstrate that Furion significantly outperforms state-of-the-art systems, achieving substantially higher throughput, lower latency, and markedly reduced abort rates under skewed and highly contended workloads.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4373-4384"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11482499","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148511019","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":"AdaPush: An Adaptive Push Framework for Graph-Propagation Based Node Similarity Computation","authors":"Yichun Yang;Rong-Hua Li;Meihao Liao;Guoren Wang","doi":"10.1109/TKDE.2026.3681914","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3681914","url":null,"abstract":"Computing graph-propagation based node similarities is a fundamental operator in many graph mining and graph learning tasks. The state-of-the-art approach to compute the graph-propagation based similarity is based on a <i>push-style</i> iterative framework. The <i>push</i> framework is very efficient when the resulting node similarity vector <inline-formula><tex-math>$bm {pi }$</tex-math></inline-formula> has a small <inline-formula><tex-math>$L1$</tex-math></inline-formula>-norm (e.g., personalized PageRank and heat kernel PageRank). However, we find that when <inline-formula><tex-math>$bm {pi }$</tex-math></inline-formula> has a large <inline-formula><tex-math>$L1$</tex-math></inline-formula>-norm (e.g., Katz scores and exponential communicability), such a framework is inefficient. To overcome this issue, we propose a novel framework, called AdaPush, which is more efficient and flexible than the state-of-the-art (SOTA) framework. Based on the AdaPushframework, we develop two new algorithms with two different carefully-designed randomized acceleration techniques, respectively. We prove that both of our new algorithms can achieve a relative-error guarantee. Additionally, a striking feature of our algorithms is that their time complexity is insensitive to <inline-formula><tex-math>$Vert pi Vert _{1}$</tex-math></inline-formula>, thus they are efficient even when <inline-formula><tex-math>$Vert pi Vert _{1}$</tex-math></inline-formula> is large. Extensive experiments on 5 large real-life datasets demonstrate that our algorithms substantially outperform the SOTA algorithms for computing Katz score and exponential communicability in terms of both running time and estimation accuracy.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4093-4106"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512389","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":"CECKG: A Credible Entity Classification Method for Knowledge Graph","authors":"Shuang Yu;Qingfeng Li;Mingyi Liu;Hanchuan Xu;Zhongjie Wang","doi":"10.1109/TKDE.2026.3688922","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3688922","url":null,"abstract":"Knowledge Graphs (KGs), with their rich semantics, friendly structure, are crucial for enhancing AI systems’ capability for understanding, reasoning, and cross-domain applications. However, KGs often face limitations in scale and quality, exhibiting incompleteness in not only missing relations (targeted by link prediction), but also missing semantic class information for numerous entities which is equally critical for schema-level semantics and downstream reasoning. There are two main issues in KG entity classification. First, common feature representation learning methods possess a ‘black box’ nature, undermining the inherent interpretability and complex semantic structure of KGs. Second, despite many studies addressing the importance of difficulty information of each instance for enhancing classifier performance, existing models often treat all entities uniformly, ignoring the impact of varying classification difficulty on the learning process. To address these issues, we propose a credible entity classification method for KG based on classification difficulty of entities, named CECKG. In this method, we first introduce an interpretable entity feature representation technique to preserve the original semantics of KGs, rather than directly mapping entity features to a low or high-dimensional vector space. Moreover, to achieve credible entity classification in KGs, we incorporate the assessment idea of degree of credibility (<bold><i>Cr</i></b>) into the design of CECKG, creating a progressive ensemble learning model that transitions from easy to difficult. The CECKG model focuses not only on the overall classification performance but also on the credibility of each entity’s prediction. To reduce the computational cost of the classification difficulty of entities, a low-cost alternative is also proposed based on the intrinsic structural properties of KGs. A series of experimental results on five public KG datasets show that our proposed method outperforms fourteen state-of-the-art entity classification models in terms of accuracy and <bold><i>Cr</i></b>.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4153-4169"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148508108","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 Federated Learning With Mean Block Difference-Based Global Aggregation and Patience-Based Local Training","authors":"Chuan Sun;Yuanyuan Chen;Xiaoli Tang;Han Yu","doi":"10.1109/TKDE.2026.3684304","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3684304","url":null,"abstract":"As neural network models grow larger and more complex, federated learning (FL) faces challenges in terms of communication and computation efficiency. To address these issues, layer-wise learning has been proposed. Existing approaches did not leverage useful properties of layer-wise learning including update locking and variations in convergence rates, thereby resulting in sub-par model performance. To bridge this gap, we propose the <underline>Fed</u>erated <underline>M</u>ean <underline>B</u>lock <underline>D</u>ifference-based global model aggregation approach with <underline>P</u>atience-based local training (<monospace>FedMBDP</monospace>). We automatically partition the neural network model into uncoupled blocks and progressively train them. Determining which blocks to train and aggregate becomes a critical task. To improve computation efficiency, we propose a patience-based local training algorithm to adaptively select training blocks, reducing computation latency. To improve communication efficiency, we introduce a mean block difference-based global model aggregation algorithm to dynamically select blocks for aggregation to minimize communication latency. We provide the convergence analysis of <monospace>FedMBDP</monospace>. Extensive experiments on three widely adopted benchmark datasets show that <monospace>FedMBDP</monospace> achieves superior performance compared to six state-of-the-art approaches. It reduces FL training latency by 26.37% compared to the best baseline, while achieving similar test accuracy.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4270-4286"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512279","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":"Counting Butterflies Over Streaming Bipartite Graphs With Duplicate Edges","authors":"Lingkai Meng;Long Yuan;Xuemin Lin;Chengjie Li;Kai Wang;Wenjie Zhang","doi":"10.1109/TKDE.2026.3682749","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3682749","url":null,"abstract":"Bipartite graphs are commonly used to model relationships between two distinct entities in real-world applications, such as user-product interactions, user-movie ratings and collaborations between authors and publications. A butterfly (a 2 × 2 bi-clique) is a critical substructure in bipartite graphs, playing a significant role in tasks like community detection, fraud detection, and link prediction. As more real-world data is presented in a streaming format, efficiently counting butterflies in streaming bipartite graphs has become increasingly important. However, most existing algorithms typically assume that duplicate edges are absent, which is hard to hold in real-world graph streams, as a result, they tend to sample edges that appear multiple times, leading to inaccurate results. The only algorithm designed to handle duplicate edges is <inline-formula><tex-math>${mathsf {FABLE}}$</tex-math></inline-formula>, but it suffers from significant limitations, including high variance, substantial time complexity, and memory inefficiency due to its reliance on a priority queue. To overcome these limitations, we introduce <inline-formula><tex-math>${mathsf {DEABC}}$</tex-math></inline-formula> (Duplicate-Edge-Aware Butterfly Counting), an innovative method that uses bucket-based priority sampling to accurately estimate the number of butterflies, accounting for duplicate edges. Compared to existing methods, <inline-formula><tex-math>${mathsf {DEABC}}$</tex-math></inline-formula> significantly reduces memory usage by storing only the essential sampled edge data while maintaining high accuracy. We provide rigorous proofs of the unbiasedness and variance bounds for <inline-formula><tex-math>${mathsf {DEABC}}$</tex-math></inline-formula>, ensuring they achieve high accuracy. We compare <inline-formula><tex-math>${mathsf {DEABC}}$</tex-math></inline-formula> with state-of-the-art algorithms on real-world streaming bipartite graphs. The results show that our <inline-formula><tex-math>${mathsf {DEABC}}$</tex-math></inline-formula> outperforms existing methods in memory efficiency and accuracy, while also achieving significantly higher throughput.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4200-4212"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148515678","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":"From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection","authors":"Yixin Liu;Shiyuan Li;Yu Zheng;Qingfeng Chen;Chengqi Zhang;Philip S. Yu;Shirui Pan","doi":"10.1109/TKDE.2026.3691902","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3691902","url":null,"abstract":"Graph anomaly detection (GAD) is critical for identifying abnormal nodes in graph-structured data from diverse domains, including cybersecurity and social networks. The existing GAD methods often focus on the learning paradigms of “one-model-for-one-dataset”, requiring dataset-specific training for each dataset to achieve optimal performance. However, this paradigm suffers from limitations, such as high computational and data costs, limited generalization and transferability to new datasets, and challenges in privacy-sensitive scenarios where access to full datasets or sufficient labels is restricted. To address these limitations, we propose a novel generalist GAD paradigm that aims to develop a unified model capable of detecting anomalies on multiple unseen datasets without retraining/fine-tuning or customization. To this end, we propose a few-shot generalist GAD method with three key designs, namely feature <u>A</u>lignment, a <u>R</u>esidual encoder, and in-<u>C</u>ontext learning, abbreviated as ARC. As a generalist approach, ARC only requires a few labeled normal samples during prediction on any unseen graphs. Specifically, ARC consists of three modules: a feature <u>A</u>lignment module to unify and align features across datasets, a <u>R</u>esidual graph encoder to capture dataset-agnostic anomaly representations, and a cross-attentive in-<u>C</u>ontext learning module to score anomalies using few-shot normal context. Building on ARC, we further introduce ARC<inline-formula><tex-math>$_{mathrm{zero}}$</tex-math></inline-formula> for the zero-shot generalist GAD setting, which selects representative pseudo-normal nodes via a pseudo-context mechanism and thus enables fully label-free inference on unseen datasets. Experiments on 17 real-world datasets demonstrate that ARC and ARC<inline-formula><tex-math>$_{mathrm{zero}}$</tex-math></inline-formula> effectively detect anomalies, exhibit strong generalization ability, and perform efficiently under few-shot and zero-shot settings.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4357-4372"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148508136","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":"Controllable Exploration-Exploitation in User-Item Interactions Toward Long-Term Recommendation Gains: A Pane-Aware Graph Transformer Architecture","authors":"Qihang Guo;Xibei Yang;Keyu Liu;Weiping Ding;Yuhua Qian","doi":"10.1109/TKDE.2026.3689197","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3689197","url":null,"abstract":"Bipartite graphs are a fundamental resource for inferring user preferences and understanding consumer decision-making behavior, driving the rapid development of graph-based recommendation systems. The challenge of feedback scarcity (i.e., sparse interactions) in graph-based recommendation systems has prompted extensive research on exploration-exploitation strategies to trade off exploration-exploitation in interactions. However, the tight coupling between exploration-exploitation behavior and bipartite graph learning poses a major obstacle to achieving the balance needed for long-term recommendation gains (i.e., enhancing diversity while maintaining accuracy). To better understand this issue, we conduct preliminary theoretical analysis and find that uneven user-item interactions heighten the risk of exploration-exploitation imbalance. Even popular graph Transformer architectures, though effective in exploration-exploitation, may still exhibit uncertain and unintended behavior, which can result in the imbalance issues. To address this problem, we propose a pane-aware graph Transformer architecture for personalized recommendation from a dynamic resource allocation perspective. Our approach builds upon graph Transformers and introduces two key modules: 1) pane partitioning and 2) a two-stage learning strategy, to explicitly intervene in the exploration-exploitation process of graph Transformers, rather than relying on the models to perform potentially uncertain and unintended balancing behavior. Specifically, the first module uses clustering and large language model reasoning to accurately constrain exploration-exploitation regions, guiding the balancing behavior of downstream graph Transformers. The second module separates training focuses to improve information allocation and ensure marginal gains. Extensive experiments on real-world datasets demonstrate that the proposed method effectively balances exploration-exploitation in user-item interactions and achieves long-term recommendation gains.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4185-4199"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148511697","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":"CACE: A Framework for Generating Counterfactual Explanations Aligned With Causal Structure via Jointly Learned Conditional Distributions","authors":"Jacob Sanderson;Hua Mao;Qiuji Yi;Wai Lok Woo","doi":"10.1109/TKDE.2026.3689207","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3689207","url":null,"abstract":"Trustworthy explanations are essential for supporting decision-making in high-stakes domains such as healthcare, finance, and environmental risk management. Counterfactual explanations provide actionable insights by revealing how small changes to input features can alter a model’s prediction. However, for such explanations to be reliable and interpretable, they must be not only valid but also plausible, reflecting realistic alternatives within the data-generating process. Existing aproaches often approximate plausibility using statistical similarity or domain constraints, neglecting the underlying causal dependencies among variables. In this work, we introduce a novel framework for generating causally plausible counterfactuals by optimizing their class-conditional likelihood under a neural structural causal model (SCM). This model provides a modular, heteroscedastic representation of structured causal knowledge, enabling probabilistic evaluation of candidate explanations, conditioned on causal relationships. Through empirical validation across synthetic, semi-synthetic, and real-world datasets, we demonstrate that our approach improves both statistical and causal plausibility without sacrificing validity or proximity. The proposed method bridges structural modeling with interpretable machine learning, offering a principled and scalable approach to trustworthy explanation in data-driven systems.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4139-4152"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512094","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 Densest Flow Queries in Transaction Flow Networks","authors":"Jiaxin Jiang;Yunxiang Zhao;Lyu Xu;Byron Choi;Bingsheng He;Shixuan Sun;Jia Chen","doi":"10.1109/TKDE.2026.3669778","DOIUrl":"https://doi.org/10.1109/TKDE.2026.3669778","url":null,"abstract":"Transaction flow networks are crucial in detecting illicit activities such as wash trading, credit card fraud, cashback arbitrage fraud, and money laundering. Our collaborator, Grab, a leader in digital payments in Southeast Asia, faces increasingly sophisticated fraud patterns in its transaction flow networks. In industry settings such as Grab’s fraud detection pipeline, identifying fraudulent activities heavily relies on detecting dense flows within transaction networks. Motivated by this practical foundation, we propose the <i><inline-formula><tex-math>$S$</tex-math><alternatives><mml:math><mml:mi>S</mml:mi></mml:math><inline-graphic></alternatives></inline-formula>-<inline-formula><tex-math>$T$</tex-math><alternatives><mml:math><mml:mi>T</mml:mi></mml:math><inline-graphic></alternatives></inline-formula> densest flow</i> (STDF) query. Given a transaction flow network <inline-formula><tex-math>$G$</tex-math></inline-formula>, a source set <inline-formula><tex-math>$S$</tex-math></inline-formula>, a sink set <inline-formula><tex-math>$T$</tex-math></inline-formula>, and a size threshold <inline-formula><tex-math>$k$</tex-math></inline-formula>, the query outputs subsets <inline-formula><tex-math>$S^{prime } subseteq S$</tex-math></inline-formula> and <inline-formula><tex-math>$T^{prime } subseteq T$</tex-math></inline-formula> such that the maximum flow from <inline-formula><tex-math>$S^{prime }$</tex-math></inline-formula> to <inline-formula><tex-math>$T^{prime }$</tex-math></inline-formula> is densest, with <inline-formula><tex-math>$|S^{prime } cup T^{prime }| geq k$</tex-math></inline-formula>. Recognizing the NP-hardness of the STDF query, we develop an efficient divide-and-conquer algorithm, <inline-formula><tex-math>$mathsf {Conan}$</tex-math></inline-formula>. Driven by industry needs for scalable and efficient solutions, we introduce an approximate flow-peeling algorithm to optimize the performance of <inline-formula><tex-math>$mathsf {Conan}$</tex-math></inline-formula>, enhancing its efficiency in processing large transaction networks. Our approach has been integrated into Grab’s fraud detection scenario, resulting in significant improvements in identifying fraudulent activities. Experiments show that <inline-formula><tex-math>$mathsf {Conan}$</tex-math></inline-formula> outperforms baseline methods by up to three orders of magnitude in runtime and more effectively identifies the densest flows. We showcase <inline-formula><tex-math>$mathsf {Conan}$</tex-math></inline-formula>’s applications in fraud detection on transaction flow networks from our industry partner, Grab, and on non-fungible tokens (NFTs).","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"38 7","pages":"4254-4269"},"PeriodicalIF":11.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512277","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}