Evidential uncertainty sampling for active learning

TL;DR

This paper introduces a simplified active learning sampling method based on evidential uncertainty, which accounts for oracle label uncertainty and outperforms traditional uncertainty sampling methods.

Contribution

It proposes novel sampling strategies using belief functions to incorporate label uncertainty and reduce computational complexity in active learning.

Findings

Proposed methods outperform standard uncertainty sampling.

Incorporates oracle label uncertainty into active learning.

Reduces computational dependence on observations.

Abstract

Recent studies in active learning, particularly in uncertainty sampling, have focused on the decomposition of model uncertainty into reducible and irreducible uncertainties. In this paper, the aim is to simplify the computational process while eliminating the dependence on observations. Crucially, the inherent uncertainty in the labels is considered, the uncertainty of the oracles. Two strategies are proposed, sampling by Klir uncertainty, which tackles the exploration-exploitation dilemma, and sampling by evidential epistemic uncertainty, which extends the concept of reducible uncertainty within the evidential framework, both using the theory of belief functions. Experimental results in active learning demonstrate that our proposed method can outperform uncertainty sampling.