Connectivity-Optimized Representation Learning via Persistent Homology
From MaRDI portal
Publication:6320826
arXiv1906.09003MaRDI QIDQ6320826
Author name not available (Why is that?)
Publication date: 21 June 2019
Abstract: We study the problem of learning representations with controllable connectivity properties. This is beneficial in situations when the imposed structure can be leveraged upstream. In particular, we control the connectivity of an autoencoder's latent space via a novel type of loss, operating on information from persistent homology. Under mild conditions, this loss is differentiable and we present a theoretical analysis of the properties induced by the loss. We choose one-class learning as our upstream task and demonstrate that the imposed structure enables informed parameter selection for modeling the in-class distribution via kernel density estimators. Evaluated on computer vision data, these one-class models exhibit competitive performance and, in a low sample size regime, outperform other methods by a large margin. Notably, our results indicate that a single autoencoder, trained on auxiliary (unlabeled) data, yields a mapping into latent space that can be reused across datasets for one-class learning.
Has companion code repository: https://github.com/c-hofer/COREL_icml2019
This page was built for publication: Connectivity-Optimized Representation Learning via Persistent Homology
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6320826)
