Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning. (arXiv:2106.12196v2 [cs.LG] UPDATED)

We propose a new method for unsupervised generative continual learning
through realignment of Variational Autoencoder's latent space. Deep generative
models suffer from catastrophic forgetting in the same way as other neural
structures. Recent generative continual learning works approach this problem
and try to learn from new data without forgetting previous knowledge. However,
those methods usually focus on artificial scenarios where examples share almost
no similarity between subsequent portions of data - an assumption not realistic
in the real-life applications of …

alignment arxiv consolidation continual knowledge learning space