English

Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks

Machine Learning 2023-01-30 v1

Abstract

As a few large-scale pre-trained models become the major choices of various applications, new challenges arise for model pruning, e.g., can we avoid pruning the same model from scratch for every downstream task? How to reuse the pruning results of previous tasks to accelerate the pruning for a new task? To address these challenges, we create a small model for a new task from the pruned models of similar tasks. We show that a few fine-tuning steps on this model suffice to produce a promising pruned-model for the new task. We study this ''meta-pruning'' from nearest tasks on two major classes of pre-trained models, convolutional neural network (CNN) and vision transformer (ViT), under a limited budget of pruning iterations. Our study begins by investigating the overlap of pruned models for similar tasks and how the overlap changes over different layers and blocks. Inspired by these discoveries, we develop a simple but effective ''Meta-Vote Pruning (MVP)'' method that significantly reduces the pruning iterations for a new task by initializing a sub-network from the pruned models of its nearest tasks. In experiments, we demonstrate MVP's advantages in accuracy, efficiency, and generalization through extensive empirical studies and comparisons with popular pruning methods over several datasets.

Keywords

Cite

@article{arxiv.2301.11560,
  title  = {Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks},
  author = {Haiyan Zhao and Tianyi Zhou and Guodong Long and Jing Jiang and Chengqi Zhang},
  journal= {arXiv preprint arXiv:2301.11560},
  year   = {2023}
}
R2 v1 2026-06-28T08:22:49.872Z