Learning a Low-Rank Feature Representation: Achieving Better Trade-Off between Stability and Plasticity in Continual Learning
This addresses the problem of catastrophic forgetting in neural networks for continual learning, offering an incremental improvement over existing methods.
The paper tackles the stability-plasticity trade-off in continual learning by proposing LRFR, a training algorithm that optimizes parameters in the null space of past tasks' feature representations and uses low-rank feature learning to increase null space dimension, achieving consistent outperformance over state-of-the-art methods on CIFAR-100 and TinyImageNet benchmarks.
In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach optimizes network parameters in the null space of the past tasks' feature representation matrix to guarantee the stability. Concurrently, we judiciously select only a subset of neurons in each layer of the network while training individual tasks to learn the past tasks' feature representation matrix in low-rank. This increases the null space dimension when designing network parameters for subsequent tasks, thereby enhancing the plasticity. Using CIFAR-100 and TinyImageNet as benchmark datasets for continual learning, the proposed approach consistently outperforms state-of-the-art methods.