Yuling Li , Kui Yu , Fei Yang , Chunfeng Shen , Ji Chang , Zerui Li , Kang Liu
{"title":"Hierarchical feature-guided prototypical network for few-shot knowledge graph completion","authors":"Yuling Li , Kui Yu , Fei Yang , Chunfeng Shen , Ji Chang , Zerui Li , Kang Liu","doi":"10.1016/j.neunet.2025.107702","DOIUrl":null,"url":null,"abstract":"<div><div>Few-shot knowledge graph completion (FKGC) aims to predict missing triples for unseen relations by observing several associated reference entity pairs. Current methods address this task by learning relation prototypes from the direct neighborhoods of corresponding reference pairs and then computing the feature similarity between the relation prototype and query triples. However, exploiting only direct neighborhoods of entities may lose some representative entity features, leading to unreliable relation prototypes. Moreover, existing methods usually assume that all feature dimensions of entities contribute equally to calculating feature similarity, ignoring the different roles of entity features in dealing with different task relations. To solve these issues, we propose a novel hierarchical feature-guided prototypical network (HPNet) for few-shot knowledge graph completion. HPNet consists of two main components: a hierarchical neighbor encoder to capture more abundant entity features by simultaneously incorporating direct and distant neighborhood information, and a feature-guided prototype learner to compare query triples with relation prototypes along task-relevant feature dimensions by considering different importance of entity features. In this way, our model is able to generate more reliable prototypes and make comparisons in a more effective manner. Extensive comparisons to related works demonstrate the superiority of the proposed HPNet.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"191 ","pages":"Article 107702"},"PeriodicalIF":6.0000,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Networks","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0893608025005829","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Few-shot knowledge graph completion (FKGC) aims to predict missing triples for unseen relations by observing several associated reference entity pairs. Current methods address this task by learning relation prototypes from the direct neighborhoods of corresponding reference pairs and then computing the feature similarity between the relation prototype and query triples. However, exploiting only direct neighborhoods of entities may lose some representative entity features, leading to unreliable relation prototypes. Moreover, existing methods usually assume that all feature dimensions of entities contribute equally to calculating feature similarity, ignoring the different roles of entity features in dealing with different task relations. To solve these issues, we propose a novel hierarchical feature-guided prototypical network (HPNet) for few-shot knowledge graph completion. HPNet consists of two main components: a hierarchical neighbor encoder to capture more abundant entity features by simultaneously incorporating direct and distant neighborhood information, and a feature-guided prototype learner to compare query triples with relation prototypes along task-relevant feature dimensions by considering different importance of entity features. In this way, our model is able to generate more reliable prototypes and make comparisons in a more effective manner. Extensive comparisons to related works demonstrate the superiority of the proposed HPNet.
期刊介绍:
Neural Networks is a platform that aims to foster an international community of scholars and practitioners interested in neural networks, deep learning, and other approaches to artificial intelligence and machine learning. Our journal invites submissions covering various aspects of neural networks research, from computational neuroscience and cognitive modeling to mathematical analyses and engineering applications. By providing a forum for interdisciplinary discussions between biology and technology, we aim to encourage the development of biologically-inspired artificial intelligence.