Revisiting Neural Networks for Continual Learning: An Architectural Perspective

TL;DR

This paper investigates how different neural network architectures influence continual learning performance, providing insights and a method to craft more effective, compact CL architectures like AlexAC and ResAC, achieving state-of-the-art results.

Contribution

It systematically analyzes the impact of architectural choices on CL and introduces ArchCraft, a search space and method for designing CL-friendly, compact neural networks.

Findings

Architectural design significantly affects CL performance.

ArchCraft produces architectures that are more parameter-efficient.

Achieves state-of-the-art CL results with highly compact models.

Abstract

Efforts to overcome catastrophic forgetting have primarily centered around developing more effective Continual Learning (CL) methods. In contrast, less attention was devoted to analyzing the role of network architecture design (e.g., network depth, width, and components) in contributing to CL. This paper seeks to bridge this gap between network architecture design and CL, and to present a holistic study on the impact of network architectures on CL. This work considers architecture design at the network scaling level, i.e., width and depth, and also at the network components, i.e., skip connections, global pooling layers, and down-sampling. In both cases, we first derive insights through systematically exploring how architectural designs affect CL. Then, grounded in these insights, we craft a specialized search space for CL and further propose a simple yet effective ArchCraft method to steer a CL-friendly architecture, namely, this method recrafts AlexNet/ResNet into AlexAC/ResAC. Experimental validation across various CL settings and scenarios demonstrates that improved architectures are parameter-efficient, achieving state-of-the-art performance of CL while being 86%, 61%, and 97% more compact in terms of parameters than the naive CL architecture in Task IL and Class IL. Code is available at https://github.com/byyx666/ArchCraft.