Topological Autoencoders


Date

2020

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

We propose a novel approach for preserving topological structures of the input space in latent representations of autoencoders. Using persistent homology, a technique from topological data analysis, we calculate topological signatures of both the input and latent space to derive a topological loss term. Under weak theoretical assumptions, we construct this loss in a differentiable manner, such that the encoding learns to retain multi-scale connectivity information. We show that our approach is theoretically well-founded and that it exhibits favourable latent representations on a synthetic manifold as well as on real-world image data sets, while preserving low reconstruction errors.

Publication status

published

Book title

Proceedings of the 37th International Conference on Machine Learning

Volume

119

Pages / Article No.

7045 - 7054

Publisher

PMLR

Event

37th International Conference on Machine Learning (ICML 2020) (virtual)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09486 - Borgwardt, Karsten M. (ehemalig) / Borgwardt, Karsten M. (former) check_circle

Notes

Due to the Coronavirus (COVID-19) the conference was conducted virtually.

Funding

155913 - Significant Pattern Mining (SNF)

Related publications and datasets