Unsupervised Anomaly Detection through Mass Repulsing Optimal Transport

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Montesuma, Eduardo Fernandes, Habazi, Adel El, Mboula, Fred Ngole
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908438983868416
author Montesuma, Eduardo Fernandes
Habazi, Adel El
Mboula, Fred Ngole
author_facet Montesuma, Eduardo Fernandes
Habazi, Adel El
Mboula, Fred Ngole
contents Detecting anomalies in datasets is a longstanding problem in machine learning. In this context, anomalies are defined as a sample that significantly deviates from the remaining data. Meanwhile, optimal transport (OT) is a field of mathematics concerned with the transportation, between two probability measures, at least effort. In classical OT, the optimal transportation strategy of a measure to itself is the identity. In this paper, we tackle anomaly detection by forcing samples to displace its mass, while keeping the least effort objective. We call this new transportation problem Mass Repulsing Optimal Transport (MROT). Naturally, samples lying in low density regions of space will be forced to displace mass very far, incurring a higher transportation cost. We use these concepts to design a new anomaly score. Through a series of experiments in existing benchmarks, and fault detection problems, we show that our algorithm improves over existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12793
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unsupervised Anomaly Detection through Mass Repulsing Optimal Transport
Montesuma, Eduardo Fernandes
Habazi, Adel El
Mboula, Fred Ngole
Machine Learning
Artificial Intelligence
Detecting anomalies in datasets is a longstanding problem in machine learning. In this context, anomalies are defined as a sample that significantly deviates from the remaining data. Meanwhile, optimal transport (OT) is a field of mathematics concerned with the transportation, between two probability measures, at least effort. In classical OT, the optimal transportation strategy of a measure to itself is the identity. In this paper, we tackle anomaly detection by forcing samples to displace its mass, while keeping the least effort objective. We call this new transportation problem Mass Repulsing Optimal Transport (MROT). Naturally, samples lying in low density regions of space will be forced to displace mass very far, incurring a higher transportation cost. We use these concepts to design a new anomaly score. Through a series of experiments in existing benchmarks, and fault detection problems, we show that our algorithm improves over existing methods.
title Unsupervised Anomaly Detection through Mass Repulsing Optimal Transport
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.12793