BestHub
Sign in
Tag

GAMLP

0 views collected around this technical thread.

DataFunTalk
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.

GAMLPGraph Neural NetworksNDLS
0 likes · 18 min read
Graph Attention Multi‑Layer Perceptron (GAMLP) and Node‑Dependent Local Smoothing (NDLS) for Scalable and Flexible Graph Neural Networks
DataFunSummit
DataFunSummit
Jan 14, 2022 · Artificial Intelligence

Graph Attention Multi‑Layer Perceptron (GAMLP) and Node‑Dependent Local Smoothing (NDLS) for Scalable and Flexible Graph Neural Networks

This presentation introduces Tencent Angel Graph's NDLS and GAMLP techniques that address GNN scalability and flexibility by adaptively selecting propagation depth per node, employing node‑wise feature and label propagation with attention mechanisms, and demonstrating superior performance on large‑scale and sparse graph benchmarks.

AttentionGAMLPGraph Neural Networks
0 likes · 16 min read
Graph Attention Multi‑Layer Perceptron (GAMLP) and Node‑Dependent Local Smoothing (NDLS) for Scalable and Flexible Graph Neural Networks