paper-with-me

Papers

Topological Autoencoders

2019-06-03 · ICML 2020 1 · Michael Moor, Max Horn, Bastian Rieck, Karsten Borgwardt

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.

📄 PDF Abstract BibTeX arXiv:1906.00722

Code (2)

BorgwardtLab/topological-autoencoders 공식 구현 pytorch
BorgwardtLab/topo-ae-distances pytorch

Tasks

Data AugmentationTopological Data Analysis

Similar Papers 제목 키워드 기반

Diffusion Variational Autoencoders

2019-01-25 · Luis A. Pérez Rey, Vlado Menkovski, Jacobus W. Portegies

A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets. To remove topological obstructions, we introduce Diffusion Variational…

Enhancing anomaly detection with topology-aware autoencoders

2025-02-14 · Vishal S. Ngairangbam, Błażej Rozwoda, Kazuki Sakurai, Michael Spannowsky

Anomaly detection in high-energy physics is essential for identifying new physics beyond the Standard Model. Autoencoders provide a signal-agnostic approach but are limited by the topology of their latent space. This wor…

Anomaly Detection

Topological Data Analysis for High-Dimensional Dynamic Process Monitoring

2026-06-18 · Angan Mukherjee, Tyler A. Soderstrom, Michael J. Kurtz, Victor M. Zavala arxiv

Real-time process monitoring requires methods that extract actionable information from high-dimensional time-series data. In this work, we present a new approach for process monitoring that combines tools of topological …

Challenging Euclidean Topological Autoencoders

2020-10-10 · NeurIPS Workshop TDA_and_Beyond 2020 12 · Michael Moor, Max Horn, Karsten Borgwardt, Bastian Rieck

Topological autoencoders (TopoAE) have demonstrated their capabilities for performing dimensionality reduction while at the same time preserving topological information of the input space. In its original formulation, t…

Dimensionality Reduction

Ensuring Topological Data-Structure Preservation under Autoencoder Compression due to Latent Space Regularization in Gauss--Legendre nodes

2023-09-15 · Chethan Krishnamurthy Ramanaik, Juan-Esteban Suarez Cardona, Anna Willmann, Pia Hanfeld 외

We formulate a data independent latent space regularisation constraint for general unsupervised autoencoders. The regularisation rests on sampling the autoencoder Jacobian in Legendre nodes, being the centre of the Gauss…