Comparing Rewinding and Fine-tuning in Neural Network Pruning

Alex Renda, Jonathan Frankle, Michael Carbin

TL;DR: Instead of fine-tuning after pruning, rewind weights or learning rate schedule to their values earlier in training and retrain from there to achieve higher accuracy when pruning neural networks.

Abstract: Many neural network pruning algorithms proceed in three steps: train the network to completion, remove unwanted structure to compress the network, and retrain the remaining structure to recover lost accuracy. The standard retraining technique, fine-tuning, trains the unpruned weights from their final trained values using a small fixed learning rate. In this paper, we compare fine-tuning to alternative retraining techniques. Weight rewinding (as proposed by Frankle et al., (2019)), rewinds unpruned weights to their values from earlier in training and retrains them from there using the original training schedule. Learning rate rewinding (which we propose) trains the unpruned weights from their final values using the same learning rate schedule as weight rewinding. Both rewinding techniques outperform fine-tuning, forming the basis of a network-agnostic pruning algorithm that matches the accuracy and compression ratios of several more network-specific state-of-the-art techniques.

Code: https://github.com/lottery-ticket/rewinding-iclr20-public

Keywords: pruning, sparsity, fine-tuning, lottery ticket

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/arxiv:2003.02389/code)