融合注意力的异构信息网络嵌入学习综述  

Heterogeneous Information Network Embedding Learning Based on Attention:a Survey

作　　者：屠佳琪 张华 常晓洁 王佶 袁书宏 TU Jiaqi;ZHANG Hua;CHANG Xiaojie;WANG Ji;YUAN Shuhong(Information Technology Center,Zhejiang University,Hangzhou 310058,China)

机构地区：[1]浙江大学信息技术中心,杭州310058

出　　处：《计算机科学与探索》2025年第1期1-29,共29页Journal of Frontiers of Computer Science and Technology

基　　金：浙江省学位委员会“十四五”研究生教育改革项目(42);宁波市科技计划项目(2022Z167)。

摘　　要：近年来,图嵌入学习已成为信息网络分析领域最常用的技术之一,其将网络对象嵌入到低维稠密向量空间的同时保留网络结构和内容特征并应用于下游分析任务。然而大多数现实网络是由多种对象类型、对象间的关系以及对象内容特征所组成的异构信息网络(HIN)。因此为了学习更有效的嵌入表达,研究者开始将注意力机制融入到异构信息网络嵌入学习中,用以区分不同层面的异构性对嵌入表达的影响程度。对现有融合注意力的异构信息网络嵌入模型进行综述,全面回顾异构信息网络嵌入在过去五年的研究历程,总结其在解决网络异构性时所面临的内容异构性、结构异构性与语义异构性三大挑战,并概括出一种通用的注意力融合模型框架;针对上述挑战,将现有注意力融合方式分为基于元路径、基于图神经网络以及面向应用场景三大类,并详细对比阐述了各类代表性模型;介绍常用的数据集、基准平台工具和评测指标;总结和探讨异构信息网络嵌入学习未来的研究方向。In recent years,graph embedding learning has become one of the most commonly used techniques in the field of information network analysis,which embeds network objects into low-dimensional dense vector spaces while preserving network structure and content characteristics.Then the learning embeddings are applied to downstream analysis tasks.However,most real-world networks are heterogeneous information networks(HIN),which are composed of multiple object types,relationships between objects and content characteristics.Therefore,in order to learn more effective embedding,researchers integrate attention mechanisms into the embedding learning of HIN to distinguish the degree of influence of different levels of heterogeneity on embedding.Therefore,this paper reviews the existing attention-integrated HIN embedding learning models.Firstly,it comprehensively reviews the research process of HIN embedding in the past five years,summarizes the three challenges it faces in solving network heterogeneity:content heterogeneity,structure heterogeneity and semantic heterogeneity,and summarizes a general framework of attention-integrated model.Secondly,in view of the above challenges,the existing attention-integrated models are divided into three categories:meta-path-based,graph neural network based and scenario-oriented,and various representative models are compared in detail.Then the common datasets,benchmark platform tools and evaluation indicators are introduced.Finally,the future research direction of HIN embedding learning is discussed.

关 键 词：异构信息网络 图嵌入学习 注意力机制 元路径 图神经网络 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]