GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
复制标题
DOI：
--
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Jiani Zhang;Xingjian Shi;Junyuan Xie;Hao Ma;Irwin King;D. Yeung
中科院分区：
文献类型：
--
作者：
Jiani Zhang;Xingjian Shi;Junyuan Xie;Hao Ma;Irwin King;D. Yeung
我们提出了一种新的网络结构，门控注意网络（GaAN），用于图上学习。与传统的多头注意机制平均消耗所有注意头不同，GaAN使用卷积子网络来控制每个注意头的重要性。我们证明了GaAN在归纳节点分类问题上的有效性。此外，以GaAN为构建块，我们构建了图门控循环单元（GGRU）来解决交通速度预测问题。在三个真实数据集上的广泛实验表明，我们的GaAN框架在这两个任务上都取得了最先进的结果。
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.