GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs

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.

Cite

Text

Zhang et al. "GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs." Conference on Uncertainty in Artificial Intelligence, 2018.

Markdown

[Zhang et al. "GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs." Conference on Uncertainty in Artificial Intelligence, 2018.](https://mlanthology.org/uai/2018/zhang2018uai-gaan/)

BibTeX

@inproceedings{zhang2018uai-gaan,
  title     = {{GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs}},
  author    = {Zhang, Jiani and Shi, Xingjian and Xie, Junyuan and Ma, Hao and King, Irwin and Yeung, Dit-Yan},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {2018},
  pages     = {339-349},
  url       = {https://mlanthology.org/uai/2018/zhang2018uai-gaan/}
}