{"title":"基于路径的图神经网络的全归纳链接预测:比较分析","authors":"","doi":"10.1016/j.neucom.2024.128484","DOIUrl":null,"url":null,"abstract":"<div><p>Recently, fully-inductive link prediction in knowledge graphs (KGs) has aimed to predict missing links between unseen–unseen entities, independently completing evolving KGs. The latest literature emphasizes path-based graph neural network (GNN) methods, which combine traditional path-based methods with popular GNN methods, possessing generalization capability, interpretability, scalability, and high model capacity under the inductive setting. This paper presents the first comparative analysis of fully-inductive link prediction using path-based GNNs. First, we comprehensively review and summarize the research of six relevant models, divided into relational digraph-based models and Bellman–Ford algorithm-based models. Based on this, we conduct a comprehensive analysis of these models in terms of effectiveness and efficiency (including runtime, memory, and learning curves), and compared them with two subgraph-based models. Furthermore, we delve into the impact of factors such as message functions, aggregation functions, and negative sampling in the loss function on path-based GNNs. Finally, we provide an outlook on future research directions.</p></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5000,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Fully-inductive link prediction with path-based graph neural network: A comparative analysis\",\"authors\":\"\",\"doi\":\"10.1016/j.neucom.2024.128484\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Recently, fully-inductive link prediction in knowledge graphs (KGs) has aimed to predict missing links between unseen–unseen entities, independently completing evolving KGs. The latest literature emphasizes path-based graph neural network (GNN) methods, which combine traditional path-based methods with popular GNN methods, possessing generalization capability, interpretability, scalability, and high model capacity under the inductive setting. This paper presents the first comparative analysis of fully-inductive link prediction using path-based GNNs. First, we comprehensively review and summarize the research of six relevant models, divided into relational digraph-based models and Bellman–Ford algorithm-based models. Based on this, we conduct a comprehensive analysis of these models in terms of effectiveness and efficiency (including runtime, memory, and learning curves), and compared them with two subgraph-based models. Furthermore, we delve into the impact of factors such as message functions, aggregation functions, and negative sampling in the loss function on path-based GNNs. Finally, we provide an outlook on future research directions.</p></div>\",\"PeriodicalId\":19268,\"journal\":{\"name\":\"Neurocomputing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.5000,\"publicationDate\":\"2024-08-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neurocomputing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0925231224012554\",\"RegionNum\":2,\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurocomputing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0925231224012554","RegionNum":2,"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}
Fully-inductive link prediction with path-based graph neural network: A comparative analysis
Recently, fully-inductive link prediction in knowledge graphs (KGs) has aimed to predict missing links between unseen–unseen entities, independently completing evolving KGs. The latest literature emphasizes path-based graph neural network (GNN) methods, which combine traditional path-based methods with popular GNN methods, possessing generalization capability, interpretability, scalability, and high model capacity under the inductive setting. This paper presents the first comparative analysis of fully-inductive link prediction using path-based GNNs. First, we comprehensively review and summarize the research of six relevant models, divided into relational digraph-based models and Bellman–Ford algorithm-based models. Based on this, we conduct a comprehensive analysis of these models in terms of effectiveness and efficiency (including runtime, memory, and learning curves), and compared them with two subgraph-based models. Furthermore, we delve into the impact of factors such as message functions, aggregation functions, and negative sampling in the loss function on path-based GNNs. Finally, we provide an outlook on future research directions.
期刊介绍:
Neurocomputing publishes articles describing recent fundamental contributions in the field of neurocomputing. Neurocomputing theory, practice and applications are the essential topics being covered.