Feedback Coding for Active Learning

TL;DR

This paper introduces a novel feedback coding approach, Approximate Posterior Matching (APM), for active learning, leveraging information theory concepts to improve efficiency and reduce computational costs in selecting data for labeling.

Contribution

The paper formulates active learning as a feedback coding problem, developing the APM algorithm that applies optimal transport theory to enhance data selection efficiency.

Findings

APM achieves comparable learning performance to existing methods.

APM reduces computational costs in active learning tasks.

The approach demonstrates the potential of information theory in active learning design.

Abstract

The iterative selection of examples for labeling in active machine learning is conceptually similar to feedback channel coding in information theory: in both tasks, the objective is to seek a minimal sequence of actions to encode information in the presence of noise. While this high-level overlap has been previously noted, there remain open questions on how to best formulate active learning as a communications system to leverage existing analysis and algorithms in feedback coding. In this work, we formally identify and leverage the structural commonalities between the two problems, including the characterization of encoder and noisy channel components, to design a new algorithm. Specifically, we develop an optimal transport-based feedback coding scheme called Approximate Posterior Matching (APM) for the task of active example selection and explore its application to Bayesian logistic regression, a popular model in active learning. We evaluate APM on a variety of datasets and demonstrate learning performance comparable to existing active learning methods, at a reduced computational cost. These results demonstrate the potential of directly deploying concepts from feedback channel coding to design efficient active learning strategies.