GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
Jiani Zhang, Xingjian Shi, Junyuan Xie, Hao Ma, Irwin King, Dit-yan Yeung
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.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Node Classification | PPI | F1 | 98.7 | GaAN |
| Node Property Prediction | ogbn-arxiv | Number of params | 1471506 | GaAN |
Related Papers
Demystifying Distributed Training of Graph Neural Networks for Link Prediction2025-06-25Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models2025-06-17Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark2025-06-14Graph Semi-Supervised Learning for Point Classification on Data Manifolds2025-06-13Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols2025-06-11Wasserstein Hypergraph Neural Network2025-06-11Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning2025-06-05iN2V: Bringing Transductive Node Embeddings to Inductive Graphs2025-06-05