Active Learning Guided by Efficient Surrogate Learners

TL;DR

This paper presents a novel active learning algorithm that uses a Gaussian process surrogate to efficiently guide data selection, reducing redundancy and improving performance without frequent retraining.

Contribution

The paper introduces a surrogate-based active learning method that updates continuously, avoiding full retraining and enhancing data sampling efficiency compared to traditional batch approaches.

Findings

Achieves performance comparable to state-of-the-art methods

Reduces redundant sampling in active learning

Demonstrates effectiveness on four benchmark datasets

Abstract

Re-training a deep learning model each time a single data point receives a new label is impractical due to the inherent complexity of the training process. Consequently, existing active learning (AL) algorithms tend to adopt a batch-based approach where, during each AL iteration, a set of data points is collectively chosen for annotation. However, this strategy frequently leads to redundant sampling, ultimately eroding the efficacy of the labeling procedure. In this paper, we introduce a new AL algorithm that harnesses the power of a Gaussian process surrogate in conjunction with the neural network principal learner. Our proposed model adeptly updates the surrogate learner for every new data instance, enabling it to emulate and capitalize on the continuous learning dynamics of the neural network without necessitating a complete retraining of the principal model for each individual label. Experiments on four benchmark datasets demonstrate that this approach yields significant enhancements, either rivaling or aligning with the performance of state-of-the-art techniques.