DataFunTalk
Jan 17, 2022 · Artificial Intelligence
Graph Attention Multi‑Layer Perceptron (GAMLP) and Node‑Dependent Local Smoothing (NDLS) for Scalable and Flexible Graph Neural Networks
This talk introduces the motivation, design, theoretical analysis, and extensive experimental results of Tencent Angel Graph's Graph Attention Multi‑Layer Perceptron (GAMLP) and Node‑Dependent Local Smoothing (NDLS), which address GNN scalability and flexibility by using node‑wise adaptive propagation, attention‑based feature fusion, and a lightweight training pipeline.
Deep LearningGAMLPGraph Neural Networks
0 likes · 18 min read