GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
Preprint
Abstract
We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head attention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to control each attention head's importance. We demonstrate the effectiveness of GaAN on the inductive node classification problem. Moreover, with GaAN as a building block, we construct the Graph Gated Recurrent Unit (GGRU) to address the traffic speed forecasting problem. Extensive experiments on three real-world datasets show that our GaAN framework achieves state-of-the-art results on both tasks.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Structured Sequence Modeling with Graph Convolutional Recurrent Networks2018
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Quantum-chemical insights from deep tensor neural networksNature Communications, 2017
- Semantic Object Parsing with Graph LSTM2016
- Wavelets on graphs via spectral graph theoryApplied and Computational Harmonic Analysis, 2011
- Gene set enrichment analysis: A knowledge-based approach for interpreting genome-wide expression profilesProceedings of the National Academy of Sciences of the United States of America, 2005