A Generic Machine Learning Framework for Fully-Unsupervised Anomaly Detection with Contaminated Data

Sep 17, 2026

Uploaded by Maeve

Anomaly detection models are commonly trained assuming anomaly-free normal data, yet real operational datasets are often contaminated by an unknown fraction of abnormal samples. Residual-based methods deteriorate under such contamination because learned “normal” regimes become unreliable. This paper presents a fully unsupervised refinement framework that improves contaminated training sets without requiring labels, using per-sample contributions to generalization while contrasting anomalies versus normal samples.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Abstract

1. Introduction

Anomaly detection assumptions and contamination

Residual-based vs truly unsupervised methods

Proposed framework and refinement idea

A Generic Machine Learning Framework for Fully-Unsupervised Anomaly Detection with Contaminated Data Markus Ulmer 1 , Jannik Zgraggen2 , and Lilach Goren Huber3 1,2,3 Zurich University of Applied Sciences, Winterthur 8401, Switzerland [markus.ulmer@zhaw.ch](markus.ulmer@zhaw.ch) [jannik.zgraggen@zhaw.ch](jannik.zgraggen@zhaw.ch) [lilach.gorenhuber@zhaw.ch](lilach.gorenhuber@zhaw.ch) ABSTRACT Anomaly detection (AD) tasks have been solved using machine learning algorithms in various domains and applications. The great majority of these algorithms use normal data to train a residual-based model and assign anomaly scores to unseen samples based on their dissimilarity with the learned normal regime. The underlying assumption of these approaches is that anomaly-free data is available for training. This is, however, often not the case in real-world operational settings, where the training data may be contaminated with an unknown fraction of abnormal samples. Training with contaminated data, in turn, inevitably leads to a deteriorated AD performance of the residual-based algorithms. In this paper we introduce a framework for a fully unsupervised reﬁnement of contaminated training data for AD tasks. The framework is generic and can be applied to any residualbased machine learning model. We demonstrate the application of the framework to two public datasets of multivariate time series machine data from different application ﬁelds. We show its clear superiority over the naive approach of training with contaminated data without reﬁnement. Moreover, we compare it to the ideal, unrealistic reference in which anomaly-free data would be available for training. The method is based on evaluating the contribution of individual samples to the generalization ability of a given model, and contrasting the contribution of anomalies with the one of normal samples. As a result, the proposed approach is comparable to, and often outperforms training with normal samples only. 1. INTRODUCTION Anomaly detection (AD) tasks are common in very diverse ﬁelds, including medical image processing, autonomous driving, fraud detection, and fault detection in industrial machines. Markus Ulmer et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. An inherent property of AD tasks is that very few or no labeled examples of anomalous behavior are provided in advance. Therefore, the most common machine learning approaches to solve these tasks are based on using exclusively normal data to train a selected prediction algorithm, which is subsequently used to infer on unseen data. The underlying assumption here is that the algorithm’s prediction errors (residuals) will be higher whenever the input sample does not belong to the learned distribution. This family of models can be referred to as residual-based models, irrespective of whether they use regression or reconstruction residuals to detect anomalies, with the most common models being reconstruction models such as principal component analysis (PCA) or various types of autoencoder (AE) neural networks. It is worth noting that these models are often termed ”unsupervised”. However, in the context of AD, they should be referred to as ”semi supervised” since they assume the availability of labeled normal data for training. In fact, such models tend to perform rather poorly whenever contamination in the form of anomalous samples is introduced into the training data. In real-world applications, however, the assumption of having anomaly-free training data does not always hold, as data contamination cannot be avoided. In this case, truly unsupervised methods, based on clustering or one-class classiﬁcation (Schlkopf, Williamson, Smola, Shawe-Taylor, & Platt, 1999), are required. Recently there has bee

FAQs

Why do residual-based anomaly detection models perform poorly on contaminated training data?

Because their residual-based training assumes anomaly-free normal data, contamination shifts the learned normal regime and lowers detection quality.

What does the proposed framework do in a fully unsupervised setting?

It refines contaminated training data in a single-step process by identifying candidate anomalies to remove, without using labels.

How is the refinement method designed to be applicable to different residual-based models?

The framework is generic: it can wrap any residual-based machine learning model (e.g., PCA, autoencoders, or regression NNs) and does not require knowledge of the contamination ratio.

Sep 17, 2026

Uploaded by Maeve