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

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

20 Mar 2018arXiv:1803.07294archive 2025-07-28

Jiani Zhang, Xingjian Shi, Junyuan Xie, Hao Ma, Irwin King, Dit-yan Yeung

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification PPI GaAN F1 98.7 #12 of 24 Archive leaderboard report
Node Property Prediction ogbn-arxiv GaAN Ext. data No #70 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GaAN Number of params 1471506 #70 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GaAN Test Accuracy 0.7197 ± 0.0024 #70 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GaAN Validation Accuracy Please tell us #70 of 86 Archive leaderboard report
Node Property Prediction ogbn-proteins GaAN Ext. data No #22 of 26 Archive leaderboard report
Node Property Prediction ogbn-proteins GaAN Number of params Please tell us #22 of 26 Archive leaderboard report
Node Property Prediction ogbn-proteins GaAN Test ROC-AUC 0.7803 ± 0.0073 #22 of 26 Archive leaderboard report
Node Property Prediction ogbn-proteins GaAN Validation ROC-AUC Please tell us #22 of 26 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: GaAN

AttentionGaANLinear LayerMulti-Head AttentionSPEEDSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections