Graph Attention Multi-Layer Perceptron

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 1 , 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 2 . CCS CONCEPTS • Mathematics of computing → Graph algorithms.