paper-with-me

홈 › Papers

Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks

2023-12-27 · Chenyang Qiu, Guoshun Nan, Tianyu Xiong, Wendi Deng, Di Wang, Zhiyang Teng, Lijuan Sun, Qimei Cui, Xiaofeng Tao

Graph convolution networks (GCNs) are extensively utilized in various graph tasks to mine knowledge from spatial data. Our study marks the pioneering attempt to quantitatively investigate the GCN robustness over omnipresent heterophilic graphs for node classification. We uncover that the predominant vulnerability is caused by the structural out-of-distribution (OOD) issue. This finding motivates us to present a novel method that aims to harden GCNs by automatically learning Latent Homophilic Structures over heterophilic graphs. We term such a methodology as LHS. To elaborate, our initial step involves learning a latent structure by employing a novel self-expressive technique based on multi-node interactions. Subsequently, the structure is refined using a pairwisely constrained dual-view contrastive learning approach. We iteratively perform the above procedure, enabling a GCN model to aggregate information in a homophilic way on heterophilic graphs. Armed with such an adaptable structure, we can properly mitigate the structural OOD threats over heterophilic graphs. Experiments on various benchmarks show the effectiveness of the proposed LHS approach for robust GCNs.

📄 PDF Abstract BibTeX arXiv:2312.16418

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningNode Classification

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

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

Task-driven Heterophilic Graph Structure Learning

2025-12-29 · Ayushman Raghuvanshi, Gonzalo Mateos, Sundeep Prabhakar Chepuri arxiv

Graph neural networks (GNNs) often struggle to learn discriminative node representations for heterophilic graphs, where connected nodes tend to have dissimilar labels and feature similarity provides weak structural cues.…

Graph structure learning

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

Exploring the Potential of Large Language Models for Heterophilic Graphs

2024-08-26 · Yuxia Wu, Shujie Li, Yuan Fang, Chuan Shi

Large language models (LLMs) have presented significant opportunities to enhance various machine learning applications, including graph neural networks (GNNs). By leveraging the vast open-world knowledge within LLMs, we …

Node ClassificationWorld Knowledge

Imbalanced Node Classification Beyond Homophilic Assumption

2023-04-28 · Jie Liu, Mengting He, Guangtao Wang, Nguyen Quoc Viet Hung 외

Imbalanced node classification widely exists in real-world networks where graph neural networks (GNNs) are usually highly inclined to majority classes and suffer from severe performance degradation on classifying minorit…

ClassificationNode Classification