计算机与现代化Issue(4)：36-41,6.DOI:10.3969/j.issn.1006-2475.2025.04.006
标签独立信息压缩的异质图表示
Label-independent Information Compression for Heterogeneous Graph Representation
摘要
Abstract
The existing methods for heterogeneous graph(HG)representation are mostly based on powerful graph neural net-works,which aggregate semantic information within and between meta-paths to embed nodes.However,these existing ap-proaches overlook the heterogeneity of nodes in HG,causing irrelevant information from neighboring nodes to spread along graph structures to higher-order nodes,disturbing the HG representation.To overcome this problem,this paper proposes a heteroge-neous graph representation method called Label-Independent Compression for Heterogeneous Graph(LICHGR).The core idea of LICHGR is,under the guidance of the Information Bottleneck,to utilize the Hilbert-Schmidt Independence Criterion to re-strict the propagation of label-independent information in heterogeneous graph while preserving label-dependent information as much as possible.Specifically,LICHGR constructs multi-faceted label-independent compression constraints among input fea-tures,hidden features within meta-paths,and true labels,extracting rich label-dependent information to enhance the quality of heterogeneous graph representation.Multiple experiments designed on three public datasets validate the effectiveness of LICHGR.关键词
图神经网络/异质图表示/信息瓶颈/希尔伯特-斯密特独立性准则Key words
graph neural network/heterogeneous graph representation/information bottleneck/Hilbert-Schmidt independence criterion分类
信息技术与安全科学引用本文复制引用
马剑,王怡菲,孟丽,何云飞,杨飞..标签独立信息压缩的异质图表示[J].计算机与现代化,2025,(4):36-41,6.基金项目
国家自然科学基金资助项目(62306011) （62306011）
安徽省自然科学基金资助项目(2108085MH303) （2108085MH303）
安徽省高校自然科学研究项目重点项目(2023AH050631) （2023AH050631）
安徽医科大学研究生科研与实践创新项目(YJS20230147) （YJS20230147）
