Papers › CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph
CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph
Silu He, Qinyao Luo, Xinsha Fu, Ling Zhao, Ronghua Du, Haifeng Li
Local Attention-guided Message Passing Mechanism (LAMP) adopted in Graph Attention Networks (GATs) is designed to adaptively learn the importance of neighboring nodes for better local aggregation on the graph, which can bring the representations of similar neighbors closer effectively, thus showing stronger discrimination ability. However, existing GATs suffer from a significant discrimination ability decline in heterophilic graphs because the high proportion of dissimilar neighbors can weaken the self-attention of the central node, jointly resulting in the deviation of the central node from similar nodes in the representation space. This kind of effect generated by neighboring nodes is called the Distraction Effect (DE) in this paper. To estimate and weaken the DE of neighboring nodes, we propose a Causally graph Attention network for Trimming heterophilic graph (CAT). To estimate the DE, since the DE are generated through two paths (grab the attention assigned to neighbors and reduce the self-attention of the central node), we use Total Effect to model DE, which is a kind of causal estimand and can be estimated from intervened data; To weaken the DE, we identify the neighbors with the highest DE (we call them Distraction Neighbors) and remove them. We adopt three representative GATs as the base model within the proposed CAT framework and conduct experiments on seven heterophilic datasets in three different sizes. Comparative experiments show that CAT can improve the node classification accuracy of all base GAT models. Ablation experiments and visualization further validate the enhancement of discrimination ability brought by CAT. The source code is available at https://github.com/GeoX-Lab/CAT.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Node Classification | Actor | CATv3-sup | Accuracy | 38.5±1.2 | #8 of 62 | Archive leaderboard | report |
| Node Classification | Chameleon | CATv3-sup | Accuracy | 69.9±1.0 | #30 of 61 | Archive leaderboard | report |
| Node Classification | Cornell | CATv3-sup | Accuracy | 88.8±2.1 | #2 of 60 | Archive leaderboard | report |
| Node Classification | Squirrel | CATv3-sup | Accuracy | 59.3±1.8 | #26 of 59 | Archive leaderboard | report |
| Node Classification | Texas | CATv3-sup | Accuracy | 83.0±2.5 | #44 of 62 | Archive leaderboard | report |
| Node Classification | Wisconsin | CATv3-sup | Accuracy | 85.6±2.1 | #42 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
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