{"title":"当异质性遇到异质图:潜在图引导的无监督表征学习","authors":"Zhixiang Shen, Zhao Kang","doi":"arxiv-2409.00687","DOIUrl":null,"url":null,"abstract":"Unsupervised heterogeneous graph representation learning (UHGRL) has gained\nincreasing attention due to its significance in handling practical graphs\nwithout labels. However, heterophily has been largely ignored, despite its\nubiquitous presence in real-world heterogeneous graphs. In this paper, we\ndefine semantic heterophily and propose an innovative framework called Latent\nGraphs Guided Unsupervised Representation Learning (LatGRL) to handle this\nproblem. First, we develop a similarity mining method that couples global\nstructures and attributes, enabling the construction of fine-grained homophilic\nand heterophilic latent graphs to guide the representation learning. Moreover,\nwe propose an adaptive dual-frequency semantic fusion mechanism to address the\nproblem of node-level semantic heterophily. To cope with the massive scale of\nreal-world data, we further design a scalable implementation. Extensive\nexperiments on benchmark datasets validate the effectiveness and efficiency of\nour proposed framework. The source code and datasets have been made available\nat https://github.com/zxlearningdeep/LatGRL.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning\",\"authors\":\"Zhixiang Shen, Zhao Kang\",\"doi\":\"arxiv-2409.00687\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Unsupervised heterogeneous graph representation learning (UHGRL) has gained\\nincreasing attention due to its significance in handling practical graphs\\nwithout labels. However, heterophily has been largely ignored, despite its\\nubiquitous presence in real-world heterogeneous graphs. In this paper, we\\ndefine semantic heterophily and propose an innovative framework called Latent\\nGraphs Guided Unsupervised Representation Learning (LatGRL) to handle this\\nproblem. First, we develop a similarity mining method that couples global\\nstructures and attributes, enabling the construction of fine-grained homophilic\\nand heterophilic latent graphs to guide the representation learning. Moreover,\\nwe propose an adaptive dual-frequency semantic fusion mechanism to address the\\nproblem of node-level semantic heterophily. To cope with the massive scale of\\nreal-world data, we further design a scalable implementation. Extensive\\nexperiments on benchmark datasets validate the effectiveness and efficiency of\\nour proposed framework. The source code and datasets have been made available\\nat https://github.com/zxlearningdeep/LatGRL.\",\"PeriodicalId\":501032,\"journal\":{\"name\":\"arXiv - CS - Social and Information Networks\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Social and Information Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.00687\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Social and Information Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.00687","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Unsupervised heterogeneous graph representation learning (UHGRL) has gained
increasing attention due to its significance in handling practical graphs
without labels. However, heterophily has been largely ignored, despite its
ubiquitous presence in real-world heterogeneous graphs. In this paper, we
define semantic heterophily and propose an innovative framework called Latent
Graphs Guided Unsupervised Representation Learning (LatGRL) to handle this
problem. First, we develop a similarity mining method that couples global
structures and attributes, enabling the construction of fine-grained homophilic
and heterophilic latent graphs to guide the representation learning. Moreover,
we propose an adaptive dual-frequency semantic fusion mechanism to address the
problem of node-level semantic heterophily. To cope with the massive scale of
real-world data, we further design a scalable implementation. Extensive
experiments on benchmark datasets validate the effectiveness and efficiency of
our proposed framework. The source code and datasets have been made available
at https://github.com/zxlearningdeep/LatGRL.