论文标题
尖峰GAT：通过尖峰神经网络学习图表
Spiking GATs: Learning Graph Attentions via Spiking Neural Network
论文作者
论文摘要
图形注意网络（GAT）已被深入研究并广泛用于图数据学习任务。现有的GAT通常采用自我注意的机制来进行图形边缘注意力学习，需要昂贵的计算。众所周知，尖峰神经网络（SNN）可以通过将输入信号数据传输到离散的尖峰列车中来执行廉价的计算，还可以返回稀疏的输出。受SNN的优点启发，在这项工作中，我们提出了一个新颖的图形尖峰注意网络（GSAT），以用于图数据表示和学习。与现有GAT中的自我注意事项机制相反，拟议的GSAT采用了SNN模块架构，这显然是节能的。此外，GSAT可以在天然中返回稀疏的注意系数，因此可以在选择性邻居上执行特征聚合，这使GSAT使GSAT执行稳健的W.R.T图形边缘噪声。几个数据集的实验结果证明了所提出的GSAT模型的有效性，能源效率和鲁棒性。
Graph Attention Networks (GATs) have been intensively studied and widely used in graph data learning tasks. Existing GATs generally adopt the self-attention mechanism to conduct graph edge attention learning, requiring expensive computation. It is known that Spiking Neural Networks (SNNs) can perform inexpensive computation by transmitting the input signal data into discrete spike trains and can also return sparse outputs. Inspired by the merits of SNNs, in this work, we propose a novel Graph Spiking Attention Network (GSAT) for graph data representation and learning. In contrast to self-attention mechanism in existing GATs, the proposed GSAT adopts a SNN module architecture which is obvious energy-efficient. Moreover, GSAT can return sparse attention coefficients in natural and thus can perform feature aggregation on the selective neighbors which makes GSAT perform robustly w.r.t graph edge noises. Experimental results on several datasets demonstrate the effectiveness, energy efficiency and robustness of the proposed GSAT model.
