AutoAL: Automated Active Learning with Differentiable Query Strategy Search

TL;DR

AutoAL introduces a differentiable search method for active learning strategies, enabling automatic selection of the most effective AL algorithms for diverse tasks, leading to improved model accuracy and data efficiency.

Contribution

This paper presents AutoAL, the first differentiable approach to automatically search and optimize active learning strategies for deep neural networks.

Findings

AutoAL outperforms individual AL algorithms in accuracy across various tasks.

AutoAL effectively adapts to different data scenarios and domains.

The method demonstrates consistent improvements over existing AL approaches.

Abstract

As deep learning continues to evolve, the need for data efficiency becomes increasingly important. Considering labeling large datasets is both time-consuming and expensive, active learning (AL) provides a promising solution to this challenge by iteratively selecting the most informative subsets of examples to train deep neural networks, thereby reducing the labeling cost. However, the effectiveness of different AL algorithms can vary significantly across data scenarios, and determining which AL algorithm best fits a given task remains a challenging problem. This work presents the first differentiable AL strategy search method, named AutoAL, which is designed on top of existing AL sampling strategies. AutoAL consists of two neural nets, named SearchNet and FitNet, which are optimized concurrently under a differentiable bi-level optimization framework. For any given task, SearchNet and FitNet are iteratively co-optimized using the labeled data, learning how well a set of candidate AL algorithms perform on that task. With the optimal AL strategies identified, SearchNet selects a small subset from the unlabeled pool for querying their annotations, enabling efficient training of the task model. Experimental results demonstrate that AutoAL consistently achieves superior accuracy compared to all candidate AL algorithms and other selective AL approaches, showcasing its potential for adapting and integrating multiple existing AL methods across diverse tasks and domains. Code is available at: https://github.com/haizailache999/AutoAL.