Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation. (arXiv:2204.02283v1 [cs.LG])

Recent research has shown that generative models with highly disentangled
representations fail to generalise to unseen combination of generative factor
values. These findings contradict earlier research which showed improved
performance in out-of-training distribution settings when compared to entangled
representations. Additionally, it is not clear if the reported failures are due
to (a) encoders failing to map novel combinations to the proper regions of the
latent space or (b) novel combinations being mapped correctly but the
decoder/downstream process is unable to …

arxiv challenge space