Large and performant neural networks are often overparameterized and can be drastically reduced in size and complexity thanks to pruning. Pruning is a group of methods, which seeks to remove redundant or unnecessary weights or groups of weights in a network. These techniques allow the creation of lightweight networks, which are particularly critical in embedded or mobile applications. In this paper, we devise an alternative pruning method that allows extracting effective subnetworks from larger untrained ones. Our method is stochastic and extracts subnetworks by exploring different topologies which are sampled using Gumbel Softmax. The latter is also used to train probability distributions which measure the relevance of weights in the sampled topologies. The resulting subnetworks are further enhanced using a highly efficient rescaling mechanism that reduces training time and improves performance. Extensive experiments conducted on CIFAR show the outperformance of our subnetwork extraction method against the related work.
翻译:大型和有性能的神经网络往往被过度分解,由于修剪,其大小和复杂性会大大降低。 Prutning是一套方法,试图在网络中消除多余或不必要的重量或重量组。这些技术可以创建轻型网络,这些网络在嵌入或移动应用中特别关键。在本文中,我们设计了一种替代的修剪方法,从较大的未受过训练的网络中提取有效的子网络。我们的方法是随机和提取子网络,方法是探索使用 Gumbel Softmax 取样的不同地形。后者还用来培训概率分布,以测量抽样表层中重量的相关性。由此产生的子网络利用高效的再缩放机制进一步得到加强,以缩短培训时间并改进性能。在CIFAR上进行的广泛实验显示我们子网络提取方法相对于相关工作的超效性能。