Papers › Self-attention Dual Embedding for Graphs with Heterophily
Self-attention Dual Embedding for Graphs with Heterophily
Yurui Lai, Taiyan Zhang, Rui Fan
Graph Neural Networks (GNNs) have been highly successful for the node classification task. GNNs typically assume graphs are homophilic, i.e. neighboring nodes are likely to belong to the same class. However, a number of real-world graphs are heterophilic, and this leads to much lower classification accuracy using standard GNNs. In this work, we design a novel GNN which is effective for both heterophilic and homophilic graphs. Our work is based on three main observations. First, we show that node features and graph topology provide different amounts of informativeness in different graphs, and therefore they should be encoded independently and prioritized in an adaptive manner. Second, we show that allowing negative attention weights when propagating graph topology information improves accuracy. Finally, we show that asymmetric attention weights between nodes are helpful. We design a GNN which makes use of these observations through a novel self-attention mechanism. We evaluate our algorithm on real-world graphs containing thousands to millions of nodes and show that we achieve state-of-the-art results compared to existing GNNs. We also analyze the effectiveness of the main components of our design on different graphs.
Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.
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 | Actor | SADE-GCN | Accuracy | 37.91 ± 0.97 | #12 of 62 | Archive leaderboard | report |
| Node Classification | Chameleon | SADE-GCN | Accuracy | 75.57±1.57 | #9 of 61 | Archive leaderboard | report |
| Node Classification | Cornell | SADE-GCN | Accuracy | 86.21±5.59 | #12 of 60 | Archive leaderboard | report |
| Node Classification | Squirrel | SADE-GCN | Accuracy | 68.20±1.57 | #9 of 59 | Archive leaderboard | report |
| Node Classification | Texas | SADE-GCN | Accuracy | 86.49±5.12 | #20 of 62 | Archive leaderboard | report |
| Node Classification | Wisconsin | SADE-GCN | Accuracy | 88.63±4.54 | #12 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.
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