论文标题
轻巧的图形卷积网络具有拓扑一致的修剪
Lightweight Graph Convolutional Networks with Topologically Consistent Magnitude Pruning
论文作者
论文摘要
图形卷积网络（GCN）目前是通过不规则数据学习的主流。这些模型依赖于捕获上下文和节点对节点关系的消息传递和注意机制。有了多头的关注，GCN变得高度准确但过大，并且它们在廉价设备上的部署需要修剪。但是，在高度制度下进行修剪通常会导致拓扑上的网络不一致，概括较弱。在本文中，我们设计了一种用于轻质GCN设计的新颖方法。我们提出的方法分析并选择具有最高幅度的子网，同时保证其拓扑一致性。后者是通过仅选择可访问且可访问的连接来获得的，这些连接实际上在评估所选子网络的评估中。在具有挑战性的FPHA数据集上进行的实验表明，我们拓扑一致的修剪方法尤其是在非常高的修剪状态下的大量增益。
Graph convolution networks (GCNs) are currently mainstream in learning with irregular data. These models rely on message passing and attention mechanisms that capture context and node-to-node relationships. With multi-head attention, GCNs become highly accurate but oversized, and their deployment on cheap devices requires their pruning. However, pruning at high regimes usually leads to topologically inconsistent networks with weak generalization. In this paper, we devise a novel method for lightweight GCN design. Our proposed approach parses and selects subnetworks with the highest magnitudes while guaranteeing their topological consistency. The latter is obtained by selecting only accessible and co-accessible connections which actually contribute in the evaluation of the selected subnetworks. Experiments conducted on the challenging FPHA dataset show the substantial gain of our topologically consistent pruning method especially at very high pruning regimes.
