Saved in:
Bibliographic Details
Main Authors: Wen, Ziting, Pizarro, Oscar, Williams, Stefan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.01101
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929592950849536
author Wen, Ziting
Pizarro, Oscar
Williams, Stefan
author_facet Wen, Ziting
Pizarro, Oscar
Williams, Stefan
contents Fine-tuning the pre-trained model with active learning holds promise for reducing annotation costs. However, this combination introduces significant computational costs, particularly with the growing scale of pre-trained models. Recent research has proposed proxy-based active learning, which pre-computes features to reduce computational costs. Yet, this approach often incurs a significant loss in active learning performance, sometimes outweighing the computational cost savings. This paper demonstrates that not all sample selection differences result in performance degradation. Furthermore, we show that suitable training methods can mitigate the decline of active learning performance caused by certain selection discrepancies. Building upon detailed analysis, we propose a novel method, aligned selection via proxy, which improves proxy-based active learning performance by updating pre-computed features and selecting a proper training method. Extensive experiments validate that our method improves the total cost of efficient active learning while maintaining computational efficiency. The code is available at \url{https://github.com/ZiTingW/asvp}.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01101
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Feature Alignment: Rethinking Efficient Active Learning via Proxy in the Context of Pre-trained Models
Wen, Ziting
Pizarro, Oscar
Williams, Stefan
Machine Learning
Artificial Intelligence
Fine-tuning the pre-trained model with active learning holds promise for reducing annotation costs. However, this combination introduces significant computational costs, particularly with the growing scale of pre-trained models. Recent research has proposed proxy-based active learning, which pre-computes features to reduce computational costs. Yet, this approach often incurs a significant loss in active learning performance, sometimes outweighing the computational cost savings. This paper demonstrates that not all sample selection differences result in performance degradation. Furthermore, we show that suitable training methods can mitigate the decline of active learning performance caused by certain selection discrepancies. Building upon detailed analysis, we propose a novel method, aligned selection via proxy, which improves proxy-based active learning performance by updating pre-computed features and selecting a proper training method. Extensive experiments validate that our method improves the total cost of efficient active learning while maintaining computational efficiency. The code is available at \url{https://github.com/ZiTingW/asvp}.
title Feature Alignment: Rethinking Efficient Active Learning via Proxy in the Context of Pre-trained Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2403.01101