FREE: Faster and Better Data-Free Meta-Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Yongxian, Hu, Zixuan, Wang, Zhenyi, Shen, Li, Yuan, Chun, Tao, Dacheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929620252622848
author Wei, Yongxian
Hu, Zixuan
Wang, Zhenyi
Shen, Li
Yuan, Chun
Tao, Dacheng
author_facet Wei, Yongxian
Hu, Zixuan
Wang, Zhenyi
Shen, Li
Yuan, Chun
Tao, Dacheng
contents Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts constrained by data privacy concerns. Current DFML methods primarily focus on the data recovery from these pre-trained models. However, they suffer from slow recovery speed and overlook gaps inherent in heterogeneous pre-trained models. In response to these challenges, we introduce the Faster and Better Data-Free Meta-Learning (FREE) framework, which contains: (i) a meta-generator for rapidly recovering training tasks from pre-trained models; and (ii) a meta-learner for generalizing to new unseen tasks. Specifically, within the module Faster Inversion via Meta-Generator, each pre-trained model is perceived as a distinct task. The meta-generator can rapidly adapt to a specific task in just five steps, significantly accelerating the data recovery. Furthermore, we propose Better Generalization via Meta-Learner and introduce an implicit gradient alignment algorithm to optimize the meta-learner. This is achieved as aligned gradient directions alleviate potential conflicts among tasks from heterogeneous pre-trained models. Empirical experiments on multiple benchmarks affirm the superiority of our approach, marking a notable speed-up (20$\times$) and performance enhancement (1.42%$\sim$4.78%) in comparison to the state-of-the-art.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00984
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FREE: Faster and Better Data-Free Meta-Learning
Wei, Yongxian
Hu, Zixuan
Wang, Zhenyi
Shen, Li
Yuan, Chun
Tao, Dacheng
Machine Learning
Computer Vision and Pattern Recognition
Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts constrained by data privacy concerns. Current DFML methods primarily focus on the data recovery from these pre-trained models. However, they suffer from slow recovery speed and overlook gaps inherent in heterogeneous pre-trained models. In response to these challenges, we introduce the Faster and Better Data-Free Meta-Learning (FREE) framework, which contains: (i) a meta-generator for rapidly recovering training tasks from pre-trained models; and (ii) a meta-learner for generalizing to new unseen tasks. Specifically, within the module Faster Inversion via Meta-Generator, each pre-trained model is perceived as a distinct task. The meta-generator can rapidly adapt to a specific task in just five steps, significantly accelerating the data recovery. Furthermore, we propose Better Generalization via Meta-Learner and introduce an implicit gradient alignment algorithm to optimize the meta-learner. This is achieved as aligned gradient directions alleviate potential conflicts among tasks from heterogeneous pre-trained models. Empirical experiments on multiple benchmarks affirm the superiority of our approach, marking a notable speed-up (20$\times$) and performance enhancement (1.42%$\sim$4.78%) in comparison to the state-of-the-art.
title FREE: Faster and Better Data-Free Meta-Learning
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.00984