IEEE Transactions on Knowledge and Data Engineering最新文献_第6页

An Amortized O(1) Lower Bound for Dynamic Time Warping in Motif Discovery Motif发现中动态时间翘曲的平摊O(1)下界

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-24 DOI: 10.1109/TKDE.2025.3544751

Zemin Chao;Hong Gao;Dongjing Miao;Jianzhong Li;Hongzhi Wang

{"title":"An Amortized O(1) Lower Bound for Dynamic Time Warping in Motif Discovery","authors":"Zemin Chao;Hong Gao;Dongjing Miao;Jianzhong Li;Hongzhi Wang","doi":"10.1109/TKDE.2025.3544751","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3544751","url":null,"abstract":"Motif discovery is a critical operation for analyzing series data in many applications. Recent works demonstrate the importance of finding motifs with Dynamic Time Warping. However, existing algorithms spend most of their time in computing lower bounds of Dynamic Time Warping to filter out the unpromising candidates. Specifically, the time complexity for computing these lower bounds is <inline-formula><tex-math>$O(L)$</tex-math></inline-formula> for each pair of subsequences, where <inline-formula><tex-math>$L$</tex-math></inline-formula> is the length of the motif (subsequences). This paper proposes two new lower bounds, called <inline-formula><tex-math>$LB_{f}$</tex-math></inline-formula> and <inline-formula><tex-math>$LB_{M}$</tex-math></inline-formula>, both of them only cost amortized <inline-formula><tex-math>$O(1)$</tex-math></inline-formula> time for each pair of subsequences. On real datasets, the proposed lower bounds are at least one magnitude faster than the state-of-the-art lower bounds used in motif discovery while still keeping satisfying effectiveness. Based on these faster lower bounds, this paper designs an efficient motif discovery algorithm that significantly reduces the cost of lower bounds. The experiments conducted on real datasets show the proposed algorithm is 5.6 times faster than the state-of-the-art algorithms on average.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2239-2252"},"PeriodicalIF":8.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769555","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}

引用次数: 0

Provenance Graph Kernel 源图核

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-24 DOI: 10.1109/TKDE.2025.3543097

David Kohan Marzagão;Trung Dong Huynh;Ayah Helal;Sean Baccas;Luc Moreau

{"title":"Provenance Graph Kernel","authors":"David Kohan Marzagão;Trung Dong Huynh;Ayah Helal;Sean Baccas;Luc Moreau","doi":"10.1109/TKDE.2025.3543097","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543097","url":null,"abstract":"Provenance is a standardised record that describes how entities, activities, and agents have influenced a piece of data; it is commonly represented as graphs with relevant labels on both their nodes and edges. With the growing adoption of provenance in a wide range of application domains, users are increasingly confronted with an abundance of graph data, which may prove challenging to process. Graph kernels, on the other hand, have been successfully used to efficiently analyse graphs. In this paper, we introduce a novel graph kernel called <italic>provenance kernel, which is inspired by and tailored for provenance data. We employ provenance kernels to classify provenance graphs from three application domains. Our evaluation shows that they perform well in terms of classification accuracy and yield competitive results when compared against existing graph kernel methods and the provenance network analytics method while more efficient in computing time. Moreover, the provenance types used by provenance kernels are a symbolic representation of a tree pattern which can, in turn, be described using the domain-agnostic vocabulary of provenance. Therefore, provenance types thus allow for the creation of explanations of predictive models built on them.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 6","pages":"3653-3668"},"PeriodicalIF":8.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896138","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}

引用次数: 0

Snoopy: Effective and Efficient Semantic Join Discovery via Proxy Columns Snoopy：通过代理列进行高效的语义连接发现

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-24 DOI: 10.1109/TKDE.2025.3545176

Yuxiang Guo;Yuren Mao;Zhonghao Hu;Lu Chen;Yunjun Gao

{"title":"Snoopy: Effective and Efficient Semantic Join Discovery via Proxy Columns","authors":"Yuxiang Guo;Yuren Mao;Zhonghao Hu;Lu Chen;Yunjun Gao","doi":"10.1109/TKDE.2025.3545176","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3545176","url":null,"abstract":"Semantic join discovery, which aims to find columns in a table repository with high semantic joinabilities to a query column, is crucial for dataset discovery. Existing methods can be divided into two categories: cell-level methods and column-level methods. However, neither of them ensures both effectiveness and efficiency simultaneously. Cell-level methods, which compute the joinability by counting cell matches between columns, enjoy ideal effectiveness but suffer poor efficiency. In contrast, column-level methods, which determine joinability only by computing the similarity of column embeddings, enjoy proper efficiency but suffer poor effectiveness due to the issues occurring in their column embeddings: (i) semantics-joinability-gap, (ii) size limit, and (iii) permutation sensitivity. To address these issues, this paper proposes to compute column embeddings via proxy columns; furthermore, a novel column-level semantic join discovery framework, <inline-formula><tex-math>${sf Snoopy}$</tex-math></inline-formula>, is presented, leveraging proxy-column-based embeddings to bridge effectiveness and efficiency. Specifically, the proposed column embeddings are derived from the implicit column-to-proxy-column relationships, which are captured by the lightweight approximate-graph-matching-based column projection. To acquire good proxy columns for guiding the column projection, we introduce a rank-aware contrastive learning paradigm. Extensive experiments on four real-world datasets demonstrate that <inline-formula><tex-math>${sf Snoopy}$</tex-math></inline-formula> outperforms SOTA column-level methods by 16% in Recall@25 and 10% in NDCG@25, and achieves superior efficiency—being at least 5 orders of magnitude faster than cell-level solutions, and 3.5× faster than existing column-level methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2971-2985"},"PeriodicalIF":8.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769391","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}

引用次数: 0

CGoFed: Constrained Gradient Optimization Strategy for Federated Class Incremental Learning 联邦类增量学习的约束梯度优化策略

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-24 DOI: 10.1109/TKDE.2025.3544605

Jiyuan Feng;Xu Yang;Liwen Liang;Weihong Han;Binxing Fang;Qing Liao

{"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}

引用次数: 0

SPIN: Sparse Portfolio Strategy With Irregular News in Fluctuating Markets SPIN：波动市场中带有不规则消息的稀疏投资组合策略

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-24 DOI: 10.1109/TKDE.2025.3545115

Mengying Zhu;Mengyuan Yang;Yan Wang;Fei Wu;Qianqiao Liang;Chaochao Chen;Hua Wei;Xiaolin Zheng

{"title":"SPIN: Sparse Portfolio Strategy With Irregular News in Fluctuating Markets","authors":"Mengying Zhu;Mengyuan Yang;Yan Wang;Fei Wu;Qianqiao Liang;Chaochao Chen;Hua Wei;Xiaolin Zheng","doi":"10.1109/TKDE.2025.3545115","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3545115","url":null,"abstract":"The sparse portfolio optimization (SPO) problem is increasingly crucial in portfolio management, focusing on selecting a few stocks with the potential for strong market performance. However, sparse portfolio strategies often face significant short-term drawdowns during periods of market volatility. To this end, a news-driven portfolio strategy offers valuable insights to capture sudden market changes. Nevertheless, it encounters two main challenges: <italic>how to reasonably map the relationships between news and stocks and <italic>how to effectively utilize the irregular timing of news releases. To tackle the SPO problem in fluctuating markets while addressing these challenges, we propose a novel news-driven sparse portfolio strategy, named SPIN. Specifically, SPIN not only leverages industry-specific group structures existing among stocks for a more reasonable news-stock mapping and models news sequential patterns based on our devised novel news-driven forecaster to handle the irregularity of news releases. We rigorously prove that SPIN achieves a sub-linear regret. Extensive experiments on three real-world datasets demonstrate SPIN's superiority over state-of-the-art portfolio strategies in terms of cumulative wealth and short-term drawdowns.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 6","pages":"3714-3727"},"PeriodicalIF":8.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896437","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}

引用次数: 0

MTD-DS: An SLA-Aware Decision Support Benchmark for Multi-Tenant Parallel DBMSs MTD-DS：多租户并行dbms的sla感知决策支持基准

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-21 DOI: 10.1109/TKDE.2025.3543727

Shaoyi Yin;Franck Morvan;Jorge Martinez-Gil;Abdelkader Hameurlain

{"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}

引用次数: 0

Model-Agnostic Dual-Side Online Fairness Learning for Dynamic Recommendation 动态推荐的模型不可知双向在线公平学习

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-21 DOI: 10.1109/TKDE.2025.3544510

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>Model-agnostic <bold>Dual-side <bold>Online <bold>Fairness 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}

引用次数: 0

Efficient PMU Data Compression Using Enhanced Graph Filtering Enabled Principal Component Analysis 有效的PMU数据压缩使用增强的图形过滤启用主成分分析

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-21 DOI: 10.1109/TKDE.2025.3544768

Manish Pandit;Ranjana Sodhi

{"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}

引用次数: 0

Transfer-and-Fusion: Integrated Link Prediction Across Knowledge Graphs 传递与融合：跨知识图谱的集成链接预测

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-20 DOI: 10.1109/TKDE.2025.3544255

Yuanning Cui;Zequn Sun;Wei Hu

{"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, 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}

引用次数: 0

Few-Shot Knowledge Graph Completion With Star and Ring Topology Information Aggregation 基于星形和环状拓扑信息聚合的知识图补全

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-02-20 DOI: 10.1109/TKDE.2025.3544202

Jing Zhao;Xinzhu Zhang;Yujia Li;Shiliang Sun

{"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}

引用次数: 0