paper-with-me

Papers

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

2024-01-18 · Chenghua Gong, Yao Cheng, Jianxiang Yu, Can Xu, Caihua Shan, Siqiang Luo, Xiang Li

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.

📄 PDF Abstract BibTeX arXiv:2401.09769

Code (2)

gongchenghua/awesome-survey-graphs-with-heterophily 공식 구현 paddle
gongchenghua/papers-graphs-with-heterophily 공식 구현 paddle

Tasks

Graph LearningSurvey

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Graph Neural Networks for Graphs with Heterophily: A Survey

2022-02-14 · Xin Zheng, Yi Wang, Yixin Liu, Ming Li 외

Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriads of graph analytic tasks and applications. In general, most GNNs depend on the homophily assumption that nodes belo…

Graph LearningSurvey

The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges

2024-07-12 · Sitao Luan, Chenqing Hua, Qincheng Lu, Liheng Ma 외

Homophily principle, \ie{} nodes with the same labels or similar attributes are more likely to be connected, has been commonly believed to be the main reason for the superiority of Graph Neural Networks (GNNs) over tradi…

Graph LearningGraph Representation LearningRepresentation Learning

Robust Learning on Heterogeneous Graphs with Heterophily: A Graph Structure Learning Approach

2026-04-30 · Yihan Zhang, Ercan E. Kuruoglu arxiv

Heterogeneous graphs with heterophily have emerged as a powerful abstraction for modeling complex real-world systems, where nodes of different types and labels interact in diverse and often non-homophilous ways. Despite …

Graph structure learningRepresentation LearningGraph Learning

Rethinking Efficiency and Redundancy in Training Large-scale Graphs

2022-09-02 · Xin Liu, Xunbin Xiong, Mingyu Yan, Runzhen Xue 외

Large-scale graphs are ubiquitous in real-world scenarios and can be trained by Graph Neural Networks (GNNs) to generate representation for downstream tasks. Given the abundant information and complex topology of a large…

Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach

2022-09-17 · Wendong Bi, Lun Du, Qiang Fu, Yanlin Wang 외

Graph Neural Networks (GNNs) are popular machine learning methods for modeling graph data. A lot of GNNs perform well on homophily graphs while having unsatisfactory performance on heterophily graphs. Recently, some rese…

Node Classification