Direct Acquisition Optimization for Low-Budget Active Learning
Keywords: Low-Budget Active Learning, Data Scarcity, Label-Efficient Learning
TL;DR: The paper presents Direct Acquisition Optimization (DAO), a novel active learning method that enhances sample selection in low-budget settings via influence function-based model updates and alternative unbiased loss reduction estimation.
Abstract: Active Learning (AL) has gained prominence in integrating data-intensive machine learning (ML) models into domains with limited labeled data. However, its effectiveness diminishes significantly when the labeling budget is low. In this paper, we first empirically observe the performance degradation of existing AL algorithms in the low-budget settings, and then introduce Direct Acquisition Optimization (DAO), a novel AL algorithm that optimizes sample selections based on expected true loss reduction. Specifically, DAO utilizes influence functions to update model parameters and incorporates an additional acquisition strategy to mitigate bias in loss estimation. This approach facilitates a more accurate estimation of the overall error reduction, without extensive computations or reliance on labeled data. Experiments demonstrate DAO’s effectiveness in low budget settings, outperforming state-of-the-arts approaches across seven benchmarks.
Submission Number: 60
Loading