Related papers: One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

URL: http://arxiv.org/abs/2405.14121v2
Date: Wed, 02 Oct 2024 09:28:42 GMT
Title: One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
Authors: Sheng-Jun Huang, Yi Li, Yiming Sun, Ying-Peng Tang,
Abstract summary: Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently. Existing AL algorithms often rely on iterative model training, which can be computationally expensive. We propose a one-shot AL method to address this challenge, which performs all label queries without repeated model training.
Score: 39.582100727546816
License:
Abstract: Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently. Existing AL algorithms often rely on iterative model training, which can be computationally expensive, particularly for deep models. In this paper, we propose a one-shot AL method to address this challenge, which performs all label queries without repeated model training. Specifically, we extract different representations of the same dataset using distinct network backbones, and actively learn the linear prediction layer on each representation via an $\ell_p$-regression formulation. The regression problems are solved approximately by sampling and reweighting the unlabeled instances based on their maximum Lewis weights across the representations. An upper bound on the number of samples needed is provided with a rigorous analysis for $p\in [1, +\infty)$. Experimental results on 11 benchmarks show that our one-shot approach achieves competitive performances with the state-of-the-art AL methods for multiple target models.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.