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.

我们提出了一种轻量级图卷积网络设计，称为 Multi-Rate Magnitude Pruning (MRMP)，它通过联合训练网络拓扑和权重来对网络进行训练。该方法是变分的，通过将学习网络的权重分布与先验分布对齐，实现了任何固定的剪枝率的具体操作，并增强了设计的轻量级 GCN 的泛化性能。此外，MRMP 通过共享权重在多个 GCN 之间进行联合训练，以在任何目标剪枝率上外推准确的网络，而无需重新训练它们的权重。对基于骨骼的识别这一具有挑战性的任务进行的大量实验表明，我们的轻量级 GCN 在非常高的剪枝程度下有显著的性能提高。