A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Chenghua, Cheng, Yao, Yu, Jianxiang, Xu, Can, Shan, Caihua, Luo, Siqiang, Li, Xiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916657404837888
author Gong, Chenghua
Cheng, Yao
Yu, Jianxiang
Xu, Can
Shan, Caihua
Luo, Siqiang
Li, Xiang
author_facet Gong, Chenghua
Cheng, Yao
Yu, Jianxiang
Xu, Can
Shan, Caihua
Luo, Siqiang
Li, Xiang
contents Graphs are structured data that models complex relations between real-world entities. Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar features, have recently attracted significant attention and found many real-world applications. Meanwhile, increasing efforts have been made to advance learning from graphs with heterophily. Various graph heterophily measures, benchmark datasets, and learning paradigms are emerging rapidly. In this survey, we comprehensively review existing works on learning from graphs with heterophily. First, we overview over 500 publications, of which more than 340 are directly related to heterophilic graphs. After that, we survey existing metrics of graph heterophily and list recent benchmark datasets. Further, we systematically categorize existing methods based on a hierarchical taxonomy including GNN models, learning paradigms and practical applications. In addition, broader topics related to graph heterophily are also included. Finally, we discuss the primary challenges of existing studies and highlight promising avenues for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2401_09769
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
Gong, Chenghua
Cheng, Yao
Yu, Jianxiang
Xu, Can
Shan, Caihua
Luo, Siqiang
Li, Xiang
Social and Information Networks
Artificial Intelligence
Machine Learning
Graphs are structured data that models complex relations between real-world entities. Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar features, have recently attracted significant attention and found many real-world applications. Meanwhile, increasing efforts have been made to advance learning from graphs with heterophily. Various graph heterophily measures, benchmark datasets, and learning paradigms are emerging rapidly. In this survey, we comprehensively review existing works on learning from graphs with heterophily. First, we overview over 500 publications, of which more than 340 are directly related to heterophilic graphs. After that, we survey existing metrics of graph heterophily and list recent benchmark datasets. Further, we systematically categorize existing methods based on a hierarchical taxonomy including GNN models, learning paradigms and practical applications. In addition, broader topics related to graph heterophily are also included. Finally, we discuss the primary challenges of existing studies and highlight promising avenues for future research.
title A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
topic Social and Information Networks
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2401.09769