Gradient Correlation Subspace Learning against Catastrophic Forgetting

TL;DR

This paper proposes Gradient Correlation Subspace Learning (GCSL), a novel approach to mitigate catastrophic forgetting in continual learning by projecting weights into a task-specific subspace that minimizes interference with previous tasks.

Contribution

GCSL introduces a method to identify and utilize a weight subspace least affected by prior tasks, enhancing continual learning performance.

Findings

Reduces catastrophic forgetting effectively.

Applicable to multiple layers and adaptable subspace sizes.

Code implementation available online.

Abstract

Efficient continual learning techniques have been a topic of significant research over the last few years. A fundamental problem with such learning is severe degradation of performance on previously learned tasks, known also as catastrophic forgetting. This paper introduces a novel method to reduce catastrophic forgetting in the context of incremental class learning called Gradient Correlation Subspace Learning (GCSL). The method detects a subspace of the weights that is least affected by previous tasks and projects the weights to train for the new task into said subspace. The method can be applied to one or more layers of a given network architectures and the size of the subspace used can be altered from layer to layer and task to task. Code will be available at \href{https://github.com/vgthengane/GCSL}{https://github.com/vgthengane/GCSL}