Mitigating Sampling Bias and Improving Robustness in Active Learning

TL;DR

This paper introduces supervised contrastive active learning and an unbiased query strategy to reduce sampling bias, enhance accuracy, robustness, and calibration, while significantly speeding up query computation.

Contribution

It proposes novel methods, SCAL and DFM, that mitigate sampling bias and improve robustness in active learning with faster query computation.

Findings

Reduces sampling bias in active learning

Achieves state-of-the-art accuracy and calibration

Outperforms in robustness to dataset shift

Abstract

This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness. We introduce supervised contrastive active learning by leveraging the contrastive loss for active learning under a supervised setting. We propose an unbiased query strategy that selects informative data samples of diverse feature representations with our methods: supervised contrastive active learning (SCAL) and deep feature modeling (DFM). We empirically demonstrate our proposed methods reduce sampling bias, achieve state-of-the-art accuracy and model calibration in an active learning setup with the query computation 26x faster than Bayesian active learning by disagreement and 11x faster than CoreSet. The proposed SCAL method outperforms by a big margin in robustness to dataset shift and out-of-distribution.