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

Jiani Zhang, Xingjian Shi, Junyuan Xie, Hao Ma, Irwin King, Dit-yan Yeung
Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, PMLR R16:338-348, 2018.

Abstract

We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head at- tention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to control each attention head’s importance. We demonstrate the effective- ness of GaAN on the inductive node classi- fication problem on large graphs. Moreover, with GaAN as a building block, we construct the Graph Gated Recurrent Unit (GGRU) to address the traffic speed forecasting prob- lem. Extensive experiments on three real- world datasets show that our GaAN framework achieves state-of-the-art results on both tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR16-zhang18a, 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 = {Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence}, pages = {338--348}, year = {2018}, editor = {Globerson, Amir and Silva, Ricardo}, volume = {R16}, series = {Proceedings of Machine Learning Research}, month = {06--10 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r16/main/assets/zhang18a/zhang18a.pdf}, url = {https://proceedings.mlr.press/r16/zhang18a.html}, abstract = {We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head at- tention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to control each attention head’s importance. We demonstrate the effective- ness of GaAN on the inductive node classi- fication problem on large graphs. Moreover, with GaAN as a building block, we construct the Graph Gated Recurrent Unit (GGRU) to address the traffic speed forecasting prob- lem. Extensive experiments on three real- world datasets show that our GaAN framework achieves state-of-the-art results on both tasks.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs %A Jiani Zhang %A Xingjian Shi %A Junyuan Xie %A Hao Ma %A Irwin King %A Dit-yan Yeung %B Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2018 %E Amir Globerson %E Ricardo Silva %F pmlr-vR16-zhang18a %I PMLR %P 338--348 %U https://proceedings.mlr.press/r16/zhang18a.html %V R16 %X We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head at- tention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to control each attention head’s importance. We demonstrate the effective- ness of GaAN on the inductive node classi- fication problem on large graphs. Moreover, with GaAN as a building block, we construct the Graph Gated Recurrent Unit (GGRU) to address the traffic speed forecasting prob- lem. Extensive experiments on three real- world datasets show that our GaAN framework achieves state-of-the-art results on both tasks. %Z Reissued by PMLR on 04 October 2026.
APA
Zhang, J., Shi, X., Xie, J., Ma, H., King, I. & Yeung, D.. (2018). GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs. Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R16:338-348 Available from https://proceedings.mlr.press/r16/zhang18a.html. Reissued by PMLR on 04 October 2026.

Related Material