Dynamically Modular and Sparse General Continual Learning
This addresses the problem of task-interference in rehearsal-based continual learning for real-world applications, representing an incremental improvement over existing methods.
The paper tackles catastrophic forgetting in deep neural networks during continual learning by introducing Dynamos, a method that uses dynamic modularity and sparsity inspired by sparse coding in the brain, and demonstrates its effectiveness on multiple datasets under challenging protocols.
Real-world applications often require learning continuously from a stream of data under ever-changing conditions. When trying to learn from such non-stationary data, deep neural networks (DNNs) undergo catastrophic forgetting of previously learned information. Among the common approaches to avoid catastrophic forgetting, rehearsal-based methods have proven effective. However, they are still prone to forgetting due to task-interference as all parameters respond to all tasks. To counter this, we take inspiration from sparse coding in the brain and introduce dynamic modularity and sparsity (Dynamos) for rehearsal-based general continual learning. In this setup, the DNN learns to respond to stimuli by activating relevant subsets of neurons. We demonstrate the effectiveness of Dynamos on multiple datasets under challenging continual learning evaluation protocols. Finally, we show that our method learns representations that are modular and specialized, while maintaining reusability by activating subsets of neurons with overlaps corresponding to the similarity of stimuli.