Differentiable Transportation Pruning

TL;DR

This paper introduces a novel differentiable pruning method for deep neural networks that optimizes sparse sub-networks, improving deployment efficiency on resource-constrained edge devices.

Contribution

It presents an end-to-end differentiable optimal transportation-based pruning technique with precise control over network size, outperforming previous methods.

Findings

Achieves state-of-the-art pruning performance across multiple datasets and models.

Effectively balances exploration and exploitation in network pruning.

Supports various sparsity budgets and granularities.

Abstract

Deep learning algorithms are increasingly employed at the edge. However, edge devices are resource constrained and thus require efficient deployment of deep neural networks. Pruning methods are a key tool for edge deployment as they can improve storage, compute, memory bandwidth, and energy usage. In this paper we propose a novel accurate pruning technique that allows precise control over the output network size. Our method uses an efficient optimal transportation scheme which we make end-to-end differentiable and which automatically tunes the exploration-exploitation behavior of the algorithm to find accurate sparse sub-networks. We show that our method achieves state-of-the-art performance compared to previous pruning methods on 3 different datasets, using 5 different models, across a wide range of pruning ratios, and with two types of sparsity budgets and pruning granularities.