Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations
This work addresses the problem of continual learning for AI systems that need to adapt to non-stationary data streams, representing an incremental improvement over existing gradient projection-based methods.
The paper tackles catastrophic forgetting in deep neural networks by proposing sparsity and heterogeneous dropout mechanisms, building on the Gradient Projection Memory framework, and demonstrates a significant performance boost on various benchmarks, including new ones like Continual Swiss Roll and ImageNet SuperDog-40.
Continual/lifelong learning from a non-stationary input data stream is a cornerstone of intelligence. Despite their phenomenal performance in a wide variety of applications, deep neural networks are prone to forgetting their previously learned information upon learning new ones. This phenomenon is called "catastrophic forgetting" and is deeply rooted in the stability-plasticity dilemma. Overcoming catastrophic forgetting in deep neural networks has become an active field of research in recent years. In particular, gradient projection-based methods have recently shown exceptional performance at overcoming catastrophic forgetting. This paper proposes two biologically-inspired mechanisms based on sparsity and heterogeneous dropout that significantly increase a continual learner's performance over a long sequence of tasks. Our proposed approach builds on the Gradient Projection Memory (GPM) framework. We leverage k-winner activations in each layer of a neural network to enforce layer-wise sparse activations for each task, together with a between-task heterogeneous dropout that encourages the network to use non-overlapping activation patterns between different tasks. In addition, we introduce two new benchmarks for continual learning under distributional shift, namely Continual Swiss Roll and ImageNet SuperDog-40. Lastly, we provide an in-depth analysis of our proposed method and demonstrate a significant performance boost on various benchmark continual learning problems.