Papers › Graph Attention Multi-Layer Perceptron
Graph Attention Multi-Layer Perceptron
Wentao Zhang, Ziqi Yin, Zeang Sheng, Yang Li, Wen Ouyang, Xiaosen Li, Yangyu Tao, Zhi Yang, Bin Cui
Graph neural networks (GNNs) have achieved great success in many graph-based applications. However, the enormous size and high sparsity level of graphs hinder their applications under industrial scenarios. Although some scalable GNNs are proposed for large-scale graphs, they adopt a fixed K-hop neighborhood for each node, thus facing the over-smoothing issue when adopting large propagation depths for nodes within sparse regions. To tackle the above issue, we propose a new GNN architecture -- Graph Attention Multi-Layer Perceptron (GAMLP), which can capture the underlying correlations between different scales of graph knowledge. We have deployed GAMLP in Tencent with the Angel platform, and we further evaluate GAMLP on both real-world datasets and large-scale industrial datasets. Extensive experiments on these 14 graph datasets demonstrate that GAMLP achieves state-of-the-art performance while enjoying high scalability and efficiency. Specifically, it outperforms GAT by 1.3\% regarding predictive accuracy on our large-scale Tencent Video dataset while achieving up to 50× training speedup. Besides, it ranks top-1 on both the leaderboards of the largest homogeneous and heterogeneous graph (i.e., ogbn-papers100M and ogbn-mag) of Open Graph Benchmark.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 Property Prediction | ogbn-mag | NARS-GAMLP+RLU | Ext. data | No | #13 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | NARS-GAMLP+RLU | Number of params | 6734882 | #13 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | NARS-GAMLP+RLU | Test Accuracy | 0.5590 ± 0.0027 | #13 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | NARS-GAMLP+RLU | Validation Accuracy | 0.5702 ± 0.0041 | #13 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | NARS-GAMLP | Ext. data | No | #18 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | NARS-GAMLP | Number of params | 6734882 | #18 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | NARS-GAMLP | Test Accuracy | 0.5396 ± 0.0018 | #18 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | NARS-GAMLP | Validation Accuracy | 0.5548 ± 0.0008 | #18 of 39 | 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