MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge

TL;DR

MEST is a novel sparse training framework designed for edge devices that enhances accuracy and speed through elastic mutation, soft memory bounds, and data efficiency, outperforming state-of-the-art methods on ImageNet.

Contribution

This work introduces MEST, a new sparse training framework with innovative enhancements for accuracy and speed on edge devices, emphasizing the importance of sparsity schemes and data efficiency.

Findings

MEST significantly improves Top-1 accuracy on ImageNet.

MEST outperforms state-of-the-art sparse training methods.

Data efficiency accelerates sparse training by identifying removable examples.

Abstract

Recently, a new trend of exploring sparsity for accelerating neural network training has emerged, embracing the paradigm of training on the edge. This paper proposes a novel Memory-Economic Sparse Training (MEST) framework targeting for accurate and fast execution on edge devices. The proposed MEST framework consists of enhancements by Elastic Mutation (EM) and Soft Memory Bound (&S) that ensure superior accuracy at high sparsity ratios. Different from the existing works for sparse training, this current work reveals the importance of sparsity schemes on the performance of sparse training in terms of accuracy as well as training speed on real edge devices. On top of that, the paper proposes to employ data efficiency for further acceleration of sparse training. Our results suggest that unforgettable examples can be identified in-situ even during the dynamic exploration of sparsity masks in the sparse training process, and therefore can be removed for further training speedup on edge devices. Comparing with state-of-the-art (SOTA) works on accuracy, our MEST increases Top-1 accuracy significantly on ImageNet when using the same unstructured sparsity scheme. Systematical evaluation on accuracy, training speed, and memory footprint are conducted, where the proposed MEST framework consistently outperforms representative SOTA works. A reviewer strongly against our work based on his false assumptions and misunderstandings. On top of the previous submission, we employ data efficiency for further acceleration of sparse training. And we explore the impact of model sparsity, sparsity schemes, and sparse training algorithms on the number of removable training examples. Our codes are publicly available at: https://github.com/boone891214/MEST.