EvoPath:利用大型语言模型为复杂的异构信息网络发现进化元路径

IF 7.4 1区 管理学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Shixuan Liu , Haoxiang Cheng , Yunfei Wang , Yue He , Changjun Fan , Zhong Liu
{"title":"EvoPath:利用大型语言模型为复杂的异构信息网络发现进化元路径","authors":"Shixuan Liu ,&nbsp;Haoxiang Cheng ,&nbsp;Yunfei Wang ,&nbsp;Yue He ,&nbsp;Changjun Fan ,&nbsp;Zhong Liu","doi":"10.1016/j.ipm.2024.103920","DOIUrl":null,"url":null,"abstract":"<div><div>Heterogeneous Information Networks (HINs) encapsulate diverse entity and relation types, with meta-paths providing essential meta-level semantics for knowledge reasoning, although their utility is constrained by discovery challenges. While Large Language Models (LLMs) offer new prospects for meta-path discovery due to their extensive knowledge encoding and efficiency, their adaptation faces challenges such as corpora bias, lexical discrepancies, and hallucination. This paper pioneers the mitigation of these challenges by presenting EvoPath, an innovative framework that leverages LLMs to efficiently identify high-quality meta-paths. EvoPath is carefully designed, with each component aimed at addressing issues that could lead to potential knowledge conflicts. With a minimal subset of HIN facts, EvoPath iteratively generates and evolves meta-paths by dynamically replaying meta-paths in the buffer with prioritization based on their scores. Comprehensive experiments on three large, complex HINs with hundreds of relations demonstrate that our framework, EvoPath, enables LLMs to generate high-quality meta-paths through effective prompting, confirming its superior performance in HIN reasoning tasks. Further ablation studies validate the effectiveness of each module within the framework.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103920"},"PeriodicalIF":7.4000,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"EvoPath: Evolutionary meta-path discovery with large language models for complex heterogeneous information networks\",\"authors\":\"Shixuan Liu ,&nbsp;Haoxiang Cheng ,&nbsp;Yunfei Wang ,&nbsp;Yue He ,&nbsp;Changjun Fan ,&nbsp;Zhong Liu\",\"doi\":\"10.1016/j.ipm.2024.103920\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Heterogeneous Information Networks (HINs) encapsulate diverse entity and relation types, with meta-paths providing essential meta-level semantics for knowledge reasoning, although their utility is constrained by discovery challenges. While Large Language Models (LLMs) offer new prospects for meta-path discovery due to their extensive knowledge encoding and efficiency, their adaptation faces challenges such as corpora bias, lexical discrepancies, and hallucination. This paper pioneers the mitigation of these challenges by presenting EvoPath, an innovative framework that leverages LLMs to efficiently identify high-quality meta-paths. EvoPath is carefully designed, with each component aimed at addressing issues that could lead to potential knowledge conflicts. With a minimal subset of HIN facts, EvoPath iteratively generates and evolves meta-paths by dynamically replaying meta-paths in the buffer with prioritization based on their scores. Comprehensive experiments on three large, complex HINs with hundreds of relations demonstrate that our framework, EvoPath, enables LLMs to generate high-quality meta-paths through effective prompting, confirming its superior performance in HIN reasoning tasks. Further ablation studies validate the effectiveness of each module within the framework.</div></div>\",\"PeriodicalId\":50365,\"journal\":{\"name\":\"Information Processing & Management\",\"volume\":\"62 1\",\"pages\":\"Article 103920\"},\"PeriodicalIF\":7.4000,\"publicationDate\":\"2024-10-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Information Processing & Management\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0306457324002796\",\"RegionNum\":1,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Processing & Management","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0306457324002796","RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

异构信息网络(HIN)封装了各种实体和关系类型,元路径为知识推理提供了重要的元级语义,但其实用性受到发现挑战的限制。虽然大语言模型(LLM)因其广泛的知识编码和高效性为元路径发现提供了新的前景,但其适应性面临着语料偏差、词汇差异和幻觉等挑战。EvoPath 是一种利用 LLMs 高效识别高质量元路径的创新框架,本文通过介绍 EvoPath 率先缓解了这些挑战。EvoPath 经过精心设计,每个组件都旨在解决可能导致潜在知识冲突的问题。EvoPath 使用最小的 HIN 事实子集,通过动态重放缓冲区中的元路径,并根据其分数确定优先级,从而迭代生成和演化元路径。在三个包含数百个关系的大型复杂 HIN 上进行的综合实验证明,我们的框架 EvoPath 能够通过有效的提示使 LLM 生成高质量的元路径,从而证实了它在 HIN 推理任务中的卓越性能。进一步的消融研究验证了该框架中每个模块的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
EvoPath: Evolutionary meta-path discovery with large language models for complex heterogeneous information networks
Heterogeneous Information Networks (HINs) encapsulate diverse entity and relation types, with meta-paths providing essential meta-level semantics for knowledge reasoning, although their utility is constrained by discovery challenges. While Large Language Models (LLMs) offer new prospects for meta-path discovery due to their extensive knowledge encoding and efficiency, their adaptation faces challenges such as corpora bias, lexical discrepancies, and hallucination. This paper pioneers the mitigation of these challenges by presenting EvoPath, an innovative framework that leverages LLMs to efficiently identify high-quality meta-paths. EvoPath is carefully designed, with each component aimed at addressing issues that could lead to potential knowledge conflicts. With a minimal subset of HIN facts, EvoPath iteratively generates and evolves meta-paths by dynamically replaying meta-paths in the buffer with prioritization based on their scores. Comprehensive experiments on three large, complex HINs with hundreds of relations demonstrate that our framework, EvoPath, enables LLMs to generate high-quality meta-paths through effective prompting, confirming its superior performance in HIN reasoning tasks. Further ablation studies validate the effectiveness of each module within the framework.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Information Processing & Management
Information Processing & Management 工程技术-计算机:信息系统
CiteScore
17.00
自引率
11.60%
发文量
276
审稿时长
39 days
期刊介绍: Information Processing and Management is dedicated to publishing cutting-edge original research at the convergence of computing and information science. Our scope encompasses theory, methods, and applications across various domains, including advertising, business, health, information science, information technology marketing, and social computing. We aim to cater to the interests of both primary researchers and practitioners by offering an effective platform for the timely dissemination of advanced and topical issues in this interdisciplinary field. The journal places particular emphasis on original research articles, research survey articles, research method articles, and articles addressing critical applications of research. Join us in advancing knowledge and innovation at the intersection of computing and information science.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信