Papers › Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph...

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

27 Dec 2023arXiv:2312.16418archive 2025-07-28

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.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor LHS Accuracy 38.87±1.0 #5 of 62 Archive leaderboard report
Node Classification Chameleon LHS Accuracy 72.31±1.6 #21 of 61 Archive leaderboard report
Node Classification Cornell LHS Accuracy 85.96±5.1 #13 of 60 Archive leaderboard report
Node Classification Squirrel LHS Accuracy 60.27±1.2 #25 of 59 Archive leaderboard report
Node Classification Texas LHS Accuracy 86.32±4.5 #21 of 62 Archive leaderboard report
Node Classification Wisconsin LHS Accuracy 88.32±2.3 #17 of 63 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive LearningConvolutionGCN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections