Self-paced Weight Consolidation for Continual Learning

TL;DR

This paper introduces a self-paced Weight Consolidation framework for continual learning that prioritizes difficult past tasks to prevent forgetting efficiently, reducing computational costs and improving performance.

Contribution

It proposes a novel self-paced regularization method that selectively consolidates knowledge from more challenging previous tasks, enhancing continual learning effectiveness.

Findings

Improves performance over existing continual learning algorithms.

Reduces computational cost by focusing on difficult tasks.

Applicable to various algorithms like EWC, MAS, and RCIL.

Abstract

Continual learning algorithms which keep the parameters of new tasks close to that of previous tasks, are popular in preventing catastrophic forgetting in sequential task learning settings. However, 1) the performance for the new continual learner will be degraded without distinguishing the contributions of previously learned tasks; 2) the computational cost will be greatly increased with the number of tasks, since most existing algorithms need to regularize all previous tasks when learning new tasks. To address the above challenges, we propose a self-paced Weight Consolidation (spWC) framework to attain robust continual learning via evaluating the discriminative contributions of previous tasks. To be specific, we develop a self-paced regularization to reflect the priorities of past tasks via measuring difficulty based on key performance indicator (i.e., accuracy). When encountering a new task, all previous tasks are sorted from "difficult" to "easy" based on the priorities. Then the parameters of the new continual learner will be learned via selectively maintaining the knowledge amongst more difficult past tasks, which could well overcome catastrophic forgetting with less computational cost. We adopt an alternative convex search to iteratively update the model parameters and priority weights in the bi-convex formulation. The proposed spWC framework is plug-and-play, which is applicable to most continual learning algorithms (e.g., EWC, MAS and RCIL) in different directions (e.g., classification and segmentation). Experimental results on several public benchmark datasets demonstrate that our proposed framework can effectively improve performance when compared with other popular continual learning algorithms.