Towards Meta-Pruning via Optimal Transport

TL;DR

This paper proposes Intra-Fusion, a novel neural network pruning method using optimal transport that achieves high accuracy without fine-tuning and reduces training time, offering a new direction in model compression.

Contribution

Intra-Fusion redefines pruning by leveraging model fusion and optimal transport, eliminating the need for importance metric design and fine-tuning.

Findings

Achieves substantial accuracy recovery without fine-tuning.

Reduces training time while maintaining performance.

Effective across various networks and datasets.

Abstract

Structural pruning of neural networks conventionally relies on identifying and discarding less important neurons, a practice often resulting in significant accuracy loss that necessitates subsequent fine-tuning efforts. This paper introduces a novel approach named Intra-Fusion, challenging this prevailing pruning paradigm. Unlike existing methods that focus on designing meaningful neuron importance metrics, Intra-Fusion redefines the overlying pruning procedure. Through utilizing the concepts of model fusion and Optimal Transport, we leverage an agnostically given importance metric to arrive at a more effective sparse model representation. Notably, our approach achieves substantial accuracy recovery without the need for resource-intensive fine-tuning, making it an efficient and promising tool for neural network compression. Additionally, we explore how fusion can be added to the pruning process to significantly decrease the training time while maintaining competitive performance. We benchmark our results for various networks on commonly used datasets such as CIFAR-10, CIFAR-100, and ImageNet. More broadly, we hope that the proposed Intra-Fusion approach invigorates exploration into a fresh alternative to the predominant compression approaches. Our code is available here: https://github.com/alexandertheus/Intra-Fusion.