Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective

TL;DR

This paper explores how network architecture influences the stability-plasticity trade-off in continual learning, proposing a dual-network framework that improves performance and compactness by leveraging architectural differences.

Contribution

It introduces Dual-Arch, a novel framework with two specialized networks for stability and plasticity, addressing architectural-level conflicts in continual learning.

Findings

Deeper networks show better plasticity under equal parameters.

Wider networks exhibit superior stability.

Dual-Arch improves existing CL methods and reduces parameter count by up to 87%.

Abstract

The quest for Continual Learning (CL) seeks to empower neural networks with the ability to learn and adapt incrementally. Central to this pursuit is addressing the stability-plasticity dilemma, which involves striking a balance between two conflicting objectives: preserving previously learned knowledge and acquiring new knowledge. While numerous CL methods aim to achieve this trade-off, they often overlook the impact of network architecture on stability and plasticity, restricting the trade-off to the parameter level. In this paper, we delve into the conflict between stability and plasticity at the architectural level. We reveal that under an equal parameter constraint, deeper networks exhibit better plasticity, while wider networks are characterized by superior stability. To address this architectural-level dilemma, we introduce a novel framework denoted Dual-Arch, which serves as a plug-in component for CL. This framework leverages the complementary strengths of two distinct and independent networks: one dedicated to plasticity and the other to stability. Each network is designed with a specialized and lightweight architecture, tailored to its respective objective. Extensive experiments demonstrate that Dual-Arch enhances the performance of existing CL methods while being up to 87% more compact in terms of parameters. Code: https://github.com/byyx666/Dual-Arch.