RSAC: Regularized Subspace Approximation Classifier for Lightweight Continuous Learning

TL;DR

This paper introduces RSAC, a lightweight and efficient classifier designed for continuous learning in resource-constrained environments, combining feature reduction and regularization to improve performance and reduce training time.

Contribution

The paper proposes RSAC, a novel regularized subspace approximation classifier that enables efficient and lightweight continuous learning suitable for edge computing applications.

Findings

RSAC outperforms prior continuous learning methods in efficiency.

RSAC achieves better accuracy with less training time.

RSAC reduces memory usage compared to existing approaches.

Abstract

Continuous learning seeks to perform the learning on the data that arrives from time to time. While prior works have demonstrated several possible solutions, these approaches require excessive training time as well as memory usage. This is impractical for applications where time and storage are constrained, such as edge computing. In this work, a novel training algorithm, regularized subspace approximation classifier (RSAC), is proposed to achieve lightweight continuous learning. RSAC contains a feature reduction module and classifier module with regularization. Extensive experiments show that RSAC is more efficient than prior continuous learning works and outperforms these works on various experimental settings.