Continual Learning via Online Leverage Score Sampling

TL;DR

This paper introduces an online leverage score sampling method for continual learning that selectively retains important data samples to prevent forgetting and improve efficiency across multiple tasks.

Contribution

It proposes a novel leverage score-based sampling approach combined with frequent directions to enable continual learning with fixed training size and reduced forgetting.

Findings

Effective in avoiding catastrophic forgetting

Maintains constant training size across tasks

Outperforms existing methods in efficiency

Abstract

In order to mimic the human ability of continual acquisition and transfer of knowledge across various tasks, a learning system needs the capability for continual learning, effectively utilizing the previously acquired skills. As such, the key challenge is to transfer and generalize the knowledge learned from one task to other tasks, avoiding forgetting and interference of previous knowledge and improving the overall performance. In this paper, within the continual learning paradigm, we introduce a method that effectively forgets the less useful data samples continuously and allows beneficial information to be kept for training of the subsequent tasks, in an online manner. The method uses statistical leverage score information to measure the importance of the data samples in every task and adopts frequent directions approach to enable a continual or life-long learning property. This effectively maintains a constant training size across all tasks. We first provide mathematical intuition for the method and then demonstrate its effectiveness in avoiding catastrophic forgetting and computational efficiency on continual learning of classification tasks when compared with the existing state-of-the-art techniques.