Kernel Continual Learning

TL;DR

This paper proposes kernel continual learning, which uses kernel methods and variational inference to effectively prevent catastrophic forgetting without memory replay, enabling more efficient and task-specific continual learning.

Contribution

It introduces a novel kernel-based continual learning framework with variational random features for task-specific kernels and reduced memory requirements.

Findings

Outperforms existing methods on four benchmarks.

Effectively prevents catastrophic forgetting.

Reduces memory size while maintaining performance.

Abstract

This paper introduces kernel continual learning, a simple but effective variant of continual learning that leverages the non-parametric nature of kernel methods to tackle catastrophic forgetting. We deploy an episodic memory unit that stores a subset of samples for each task to learn task-specific classifiers based on kernel ridge regression. This does not require memory replay and systematically avoids task interference in the classifiers. We further introduce variational random features to learn a data-driven kernel for each task. To do so, we formulate kernel continual learning as a variational inference problem, where a random Fourier basis is incorporated as the latent variable. The variational posterior distribution over the random Fourier basis is inferred from the coreset of each task. In this way, we are able to generate more informative kernels specific to each task, and, more importantly, the coreset size can be reduced to achieve more compact memory, resulting in more efficient continual learning based on episodic memory. Extensive evaluation on four benchmarks demonstrates the effectiveness and promise of kernels for continual learning.