How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation
arXiv:2102.02805
Abstract
Catastrophic forgetting undermines the effectiveness of deep neural networks (DNNs) in scenarios such as continual learning and lifelong learning. While several methods have been proposed to tackle this problem, there is limited work explaining why these methods work well. This paper has the goal of better explaining a popularly used technique for avoiding catastrophic forgetting: quadratic regularization. We show that quadratic regularizers prevent forgetting of past tasks by interpolating current and previous values of model parameters at every training iteration. Over multiple training iterations, this interpolation operation reduces the learning rates of more important model parameters, thereby minimizing their movement. Our analysis also reveals two drawbacks of quadratic regularization: (a) dependence of parameter interpolation on training hyperparameters, which often leads to training instability and (b) assignment of lower importance to deeper layers, which are generally the place forgetting occurs in DNNs. Via a simple modification to the order of operations, we show these drawbacks can be easily avoided, resulting in 6.2\% higher average accuracy at 4.5\% lower average forgetting. We confirm the robustness of our results by training over 2000 models in different settings. Code available at \url{https://github.com/EkdeepSLubana/QRforgetting}
arXiv commentCamera-ready for Conference on Lifelong Learning Agents (CoLLAs), 2022
References in corpus (10)
- Overcoming catastrophic forgetting in neural networks
- Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
- Continual Learning Through Synaptic Intelligence
- Efficient Lifelong Learning with A-GEM
- Similarity of Neural Network Representations Revisited
- On Tiny Episodic Memories in Continual Learning
- Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
- Towards Robust Evaluations of Continual Learning
- Functional Regularisation for Continual Learning with Gaussian Processes
- Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint