Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating

Yixin Liu, Yizhen Zheng, Daokun Zhang, Vincent C.S. Lee, Shirui Pan

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

17 Citations (Scopus)

Abstract

Unsupervised graph representation learning (UGRL) has drawn increasing research attention and achieved promising results in several graph analytic tasks. Relying on the homophily assumption, existing UGRL methods tend to smooth the learned node representations along all edges, ignoring the existence of heterophilic edges that connect nodes with distinct attributes. As a result, current methods are hard to generalize to heterophilic graphs where dissimilar nodes are widely connected, and also vulnerable to adversarial attacks. To address this issue, we propose a novel unsupervised Graph Representation learning method with Edge hEterophily discriminaTing (GREET) which learns representations by discriminating and leveraging homophilic edges and heterophilic edges. To distinguish two types of edges, we build an edge discriminator that infers edge homophily/heterophily from feature and structure information. We train the edge discriminator in an unsupervised way through minimizing the crafted pivot-anchored ranking loss, with randomly sampled node pairs acting as pivots. Node representations are learned through contrasting the dual-channel encodings obtained from the discriminated homophilic and heterophilic edges. With an effective interplaying scheme, edge discriminating and representation learning can mutually boost each other during the training phase. We conducted extensive experiments on 14 benchmark datasets and multiple learning scenarios to demonstrate the superiority of GREET.

Original languageEnglish
Title of host publicationAAAI-23 Technical Tracks 4
EditorsBrian Williams, Yiling Chen, Jennifer Neville
PublisherAAAI Press
Pages4516-4524
Number of pages9
ISBN (Electronic)9781577358800
Publication statusPublished - 27 Jun 2023
Externally publishedYes
Event37th AAAI Conference on Artificial Intelligence, AAAI 2023 - Washington, United States
Duration: 7 Feb 202314 Feb 2023

Publication series

NameProceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
Volume37

Conference

Conference37th AAAI Conference on Artificial Intelligence, AAAI 2023
Country/TerritoryUnited States
CityWashington
Period7/02/2314/02/23

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating'. Together they form a unique fingerprint.

Cite this