In this paper, we devise a novel lightweight Graph Convolutional Network (GCN) design dubbed as Multi-Rate Magnitude Pruning (MRMP) that jointly trains network topology and weights. Our method is variational and proceeds by aligning the weight distribution of the learned networks with an a priori distribution. In the one hand, this allows implementing any fixed pruning rate, and also enhancing the generalization performances of the designed lightweight GCNs. In the other hand, MRMP achieves a joint training of multiple GCNs, on top of shared weights, in order to extrapolate accurate networks at any targeted pruning rate without retraining their weights. Extensive experiments conducted on the challenging task of skeleton-based recognition show a substantial gain of our lightweight GCNs particularly at very high pruning regimes.

翻译：本文提出了一种新颖的轻量级图卷积网络（GCN）设计方案，称为多速率幅度剪枝（MRMP），该方案联合训练网络拓扑结构与权重。我们的方法基于变分原理，通过将所学网络的权重分布与先验分布对齐来实现。一方面，该方法能够实现任意固定剪枝率，同时增强所设计的轻量级GCN的泛化性能。另一方面，MRMP在共享权重的基础上实现了多个GCN的联合训练，从而能够外推任意目标剪枝率下的精确网络，无需重新训练其权重。在基于骨架识别的挑战性任务上开展的大量实验表明，我们的轻量级GCN取得了显著性能提升，尤其是在极高剪枝率场景下。