Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning

About

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.

Zhixiang Shen, Zhao Kang• 2024

Related benchmarks

TaskDatasetResultRank
Node ClassificationChameleon
Accuracy57.02
867
Node ClassificationCornell
Accuracy62.16
851
Node ClassificationSquirrel
Accuracy38.07
786
Node ClassificationRoman-Empire
Accuracy30.1
327
Node Classificationamazon-ratings
Accuracy38.38
309
Node ClassificationComputers
Accuracy64.61
145
Node ClassificationPDNS
Accuracy94.5
19
Node ClassificationRCDD
Accuracy/F1 Score80.01
19
Node Classificationogbn-mag
Accuracy/F1 Score46.07
19
Node Classificationoag-cs
Accuracy/F1 Score21.55
19
Showing 10 of 13 rows

Other info

Follow for update