Gradient based sample selection for online continual learning

TL;DR

This paper introduces a gradient-based sample selection method for online continual learning that enhances replay buffer diversity without relying on task boundaries, improving learning stability and performance.

Contribution

It formulates sample selection as a constraint reduction problem and develops an efficient greedy algorithm that outperforms existing methods relying on task boundaries.

Findings

The proposed method achieves comparable or better results than state-of-the-art approaches.

It does not depend on task boundary information, unlike many previous methods.

The greedy algorithm is computationally efficient and effective in diverse continual learning scenarios.

Abstract

A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural networks. To prevent forgetting, a replay buffer is usually employed to store the previous data for the purpose of rehearsal. Previous works often depend on task boundary and i.i.d. assumptions to properly select samples for the replay buffer. In this work, we formulate sample selection as a constraint reduction problem based on the constrained optimization view of continual learning. The goal is to select a fixed subset of constraints that best approximate the feasible region defined by the original constraints. We show that it is equivalent to maximizing the diversity of samples in the replay buffer with parameters gradient as the feature. We further develop a greedy alternative that is cheap and efficient. The advantage of the proposed method is demonstrated by comparing to other alternatives under the continual learning setting. Further comparisons are made against state of the art methods that rely on task boundaries which show comparable or even better results for our method.