TY - CHAP

T1 - Studying properties of water data using manifold-aware anomaly detectors

AU - Paulsen, Tino

AU - Brefeld, Ulf

PY - 2024/4/23

Y1 - 2024/4/23

N2 - Deep learning methods, especially the family of autoencoder architectures, exhibit state-of-the-art detection rates in anomaly detection tasks. Additionally, recent results show that learning latent spaces with deep architectures on Riemannian manifolds may further improve performances as well as related interpolation tasks. In this paper, we study the use of Riemannian manifolds with variational autoencoders (VAEs) for anomaly detection on data from water providers. Besides traditional embeddings in Euclidean space, we study embeddings in Poincaré disc, spheres, and Stiefel manifolds, where in general, the Poincaré disc is often preferred for data with hierarchical structures, embeddings in spheres suggests itself for cyclical structures and the Stiefel manifold is well suited for time-dependent data. Data from water providers clearly meets all three criteria and we report on empirical results with the different manifolds as latent spaces and compare their detection performance to that of standard Euclidean embeddings.

AB - Deep learning methods, especially the family of autoencoder architectures, exhibit state-of-the-art detection rates in anomaly detection tasks. Additionally, recent results show that learning latent spaces with deep architectures on Riemannian manifolds may further improve performances as well as related interpolation tasks. In this paper, we study the use of Riemannian manifolds with variational autoencoders (VAEs) for anomaly detection on data from water providers. Besides traditional embeddings in Euclidean space, we study embeddings in Poincaré disc, spheres, and Stiefel manifolds, where in general, the Poincaré disc is often preferred for data with hierarchical structures, embeddings in spheres suggests itself for cyclical structures and the Stiefel manifold is well suited for time-dependent data. Data from water providers clearly meets all three criteria and we report on empirical results with the different manifolds as latent spaces and compare their detection performance to that of standard Euclidean embeddings.

KW - Informatics

UR - https://itrust.sutd.edu.sg/first-international-conference-on-the-design-of-cyber-secure-water-plants-dcs-water24/paper-submission-dcs-water24/

UR - https://www.mdpi.com/journal/water/special_issues/7UA9S2ASB0

M3 - Article in conference proceedings

T3 - Water

BT - Design of Cyber-Secure Water Plants

A2 - Mathur, Aditya

A2 - Zhou, Jianying

A2 - Raman, Gauthama

PB - MDPI AG

T2 - First International Conference on the design of cyber-secure water plants - DCS-Water'24

Y2 - 23 April 2024 through 24 April 2024

ER -