Topological Continual Learning with Wasserstein Distance and Barycenter
This addresses the problem of catastrophic forgetting in neural networks for continual learning applications, representing an incremental improvement by combining topological regularization with existing memory techniques.
The paper tackles catastrophic forgetting in continual learning by proposing a topological regularization method that penalizes cycle structures in neural networks using persistent homology and optimal transport, and demonstrates its effectiveness with shallow and deep networks on image classification datasets.
Continual learning in neural networks suffers from a phenomenon called catastrophic forgetting, in which a network quickly forgets what was learned in a previous task. The human brain, however, is able to continually learn new tasks and accumulate knowledge throughout life. Neuroscience findings suggest that continual learning success in the human brain is potentially associated with its modular structure and memory consolidation mechanisms. In this paper we propose a novel topological regularization that penalizes cycle structure in a neural network during training using principled theory from persistent homology and optimal transport. The penalty encourages the network to learn modular structure during training. The penalization is based on the closed-form expressions of the Wasserstein distance and barycenter for the topological features of a 1-skeleton representation for the network. Our topological continual learning method combines the proposed regularization with a tiny episodic memory to mitigate forgetting. We demonstrate that our method is effective in both shallow and deep network architectures for multiple image classification datasets.