Papers › Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
Sitao Luan, Chenqing Hua, Qincheng Lu, Jiaqi Zhu, Mingde Zhao, Shuyuan Zhang, Xiao-Wen Chang, Doina Precup
Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using the graph structures based on the relational inductive bias (homophily assumption). Though GNNs are believed to outperform NNs in real-world tasks, performance advantages of GNNs over graph-agnostic NNs seem not generally satisfactory. Heterophily has been considered as a main cause and numerous works have been put forward to address it. In this paper, we first show that not all cases of heterophily are harmful for GNNs with aggregation operation. Then, we propose new metrics based on a similarity matrix which considers the influence of both graph structure and input features on GNNs. The metrics demonstrate advantages over the commonly used homophily metrics by tests on synthetic graphs. From the metrics and the observations, we find some cases of harmful heterophily can be addressed by diversification operation. With this fact and knowledge of filterbanks, we propose the Adaptive Channel Mixing (ACM) framework to adaptively exploit aggregation, diversification and identity channels in each GNN layer to address harmful heterophily. We validate the ACM-augmented baselines with 10 real-world node classification tasks. They consistently achieve significant performance gain and exceed the state-of-the-art GNNs on most of the tasks without incurring significant computational burden.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Node Classification | Citeseer | ACMII-Snowball-2 | Accuracy | 82.07 ± 1.04 | #1 of 71 | Archive leaderboard | report |
| Node Classification | Citeseer | ACM-GCN | Accuracy | 81.68 ± 0.97 | #2 of 71 | Archive leaderboard | report |
| Node Classification | Citeseer | ACM-Snowball-2 | Accuracy | 81.58 ± 1.23 | #3 of 71 | Archive leaderboard | report |
| Node Classification | Citeseer | ACMII-Snowball-3 | Accuracy | 81.56 ± 1.15 | #4 of 71 | Archive leaderboard | report |
| Node Classification | Cora | ACMII-Snowball-3 | Accuracy | 89.36% ± 1.26% | #3 of 73 | Archive leaderboard | report |
| Node Classification | Cora | ACMII-GCN | Accuracy | 88.95% ± 1.04% | #4 of 73 | Archive leaderboard | report |
| Node Classification | Cora | ACM-Snowball-2 | Accuracy | 88.83% ± 1.49% | #5 of 73 | Archive leaderboard | report |
| Node Classification | Cora | ACM-GCN | Accuracy | 88.62% ± 1.22% | #8 of 73 | Archive leaderboard | report |
| Node Classification | Pubmed | ACMII-Snowball-3 | Accuracy | 91.31 ± 0.6 | #3 of 70 | Archive leaderboard | report |
| Node Classification | Pubmed | ACM-GCN | Accuracy | 90.74 ± 0.5 | #4 of 70 | Archive leaderboard | report |
| Node Classification | Pubmed | ACMII-Snowball-2 | Accuracy | 90.56 ± 0.39 | #6 of 70 | 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.
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