paper-with-me

홈 › Papers

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

2024-07-12 · Sitao Luan, Chenqing Hua, Qincheng Lu, Liheng Ma, Lirong Wu, Xinyu Wang, Minkai Xu, Xiao-Wen Chang, Doina Precup, Rex Ying, Stan Z. Li, Jian Tang, Guy Wolf, Stefanie Jegelka

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 traditional Neural Networks (NNs) on graph-structured data, especially on node-level tasks. However, recent work has identified a non-trivial set of datasets where GNN's performance compared to the NN's is not satisfactory. Heterophily, i.e. low homophily, has been considered the main cause of this empirical observation. People have begun to revisit and re-evaluate most existing graph models, including graph transformer and its variants, in the heterophily scenario across various kinds of graphs, e.g. heterogeneous graphs, temporal graphs and hypergraphs. Moreover, numerous graph-related applications are found to be closely related to the heterophily problem. In the past few years, considerable effort has been devoted to studying and addressing the heterophily issue. In this survey, we provide a comprehensive review of the latest progress on heterophilic graph learning, including an extensive summary of benchmark datasets and evaluation of homophily metrics on synthetic graphs, meticulous classification of the most updated supervised and unsupervised learning methods, thorough digestion of the theoretical analysis on homophily/heterophily, and broad exploration of the heterophily-related applications. Notably, through detailed experiments, we are the first to categorize benchmark heterophilic datasets into three sub-categories: malignant, benign and ambiguous heterophily. Malignant and ambiguous datasets are identified as the real challenging datasets to test the effectiveness of new models on the heterophily challenge. Finally, we propose several challenges and future directions for heterophilic graph representation learning.

📄 PDF Abstract BibTeX arXiv:2407.09618

Code (0)

등록된 구현이 없습니다.

Tasks

Graph LearningGraph Representation LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
LapEigen 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts

2024-08-18 · Jinluan Yang, Zhengyu Chen, Teng Xiao, Wenqiao Zhang 외

Heterophilic Graph Neural Networks (HGNNs) have shown promising results for semi-supervised learning tasks on graphs. Notably, most real-world heterophilic graphs are composed of a mixture of nodes with different neighbo…

Data AugmentationNode Classification

$p$-Laplacian Based Graph Neural Networks

2021-11-14 · Guoji Fu, Peilin Zhao, Yatao Bian

Graph neural networks (GNNs) have demonstrated superior performance for semi-supervised node classification on graphs, as a result of their ability to exploit node features and topological information simultaneously. How…

Node Classification

Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?

2023-06-02 · NeurIPS 2023 11 · Haitao Mao, Zhikai Chen, Wei Jin, Haoyu Han 외

Recent studies on Graph Neural Networks(GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both homophilic and certain heterophilic graphs. Notably, m…

AllNode Classification

Label-Wise Graph Convolutional Network for Heterophilic Graphs

2021-10-15 · Enyan Dai, Shijie Zhou, Zhimeng Guo, Suhang Wang

Graph Neural Networks (GNNs) have achieved remarkable performance in modeling graphs for various applications. However, most existing GNNs assume the graphs exhibit strong homophily in node labels, i.e., nodes with simil…

Node ClassificationRepresentation Learning

Beyond Fixed Depth: Adaptive Graph Neural Networks for Node Classification Under Varying Homophily

2025-11-10 · Asela Hevapathige, Asiri Wijesinghe, Ahad N. Zehmakan arxiv

Graph Neural Networks (GNNs) have achieved significant success in addressing node classification tasks. However, the effectiveness of traditional GNNs degrades on heterophilic graphs, where connected nodes often belong t…

Node Classification