Real-Time Evaluation in Online Continual Learning: A New Hope

TL;DR

This paper introduces a practical real-time evaluation framework for online continual learning, emphasizing computational efficiency, and reveals that simple baselines outperform complex methods in realistic, large-scale scenarios.

Contribution

It proposes a new real-time evaluation method for CL, highlighting the importance of computational costs and challenging the effectiveness of existing methods.

Findings

Simple baseline outperforms state-of-the-art CL methods in real-time settings.

Most existing CL methods are not competitive under practical, time-constrained conditions.

Current CL literature often targets unrealistic stream assumptions.

Abstract

Current evaluations of Continual Learning (CL) methods typically assume that there is no constraint on training time and computation. This is an unrealistic assumption for any real-world setting, which motivates us to propose: a practical real-time evaluation of continual learning, in which the stream does not wait for the model to complete training before revealing the next data for predictions. To do this, we evaluate current CL methods with respect to their computational costs. We conduct extensive experiments on CLOC, a large-scale dataset containing 39 million time-stamped images with geolocation labels. We show that a simple baseline outperforms state-of-the-art CL methods under this evaluation, questioning the applicability of existing methods in realistic settings. In addition, we explore various CL components commonly used in the literature, including memory sampling strategies and regularization approaches. We find that all considered methods fail to be competitive against our simple baseline. This surprisingly suggests that the majority of existing CL literature is tailored to a specific class of streams that is not practical. We hope that the evaluation we provide will be the first step towards a paradigm shift to consider the computational cost in the development of online continual learning methods.