# (Predictable) Performance Bias in Unsupervised Anomaly Detection

arXiv: https://arxiv.org/abs/2309.14198 · HTML: https://mlsanity.com/paper/2309.14198/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 13 of 13)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study](https://mlsanity.com/paper/2004.03271/) (2020)
- [Disparities in Dermatology AI: Assessments Using Diverse Clinical Images](https://mlsanity.com/paper/2111.08006/) (2021)
- [Improving the Fairness of Chest X-ray Classifiers](https://mlsanity.com/paper/2203.12609/) (2022)
- [FairOD: Fairness-aware Outlier Detection](https://mlsanity.com/paper/2012.03063/) (2020)
- [Towards Fair Deep Anomaly Detection](https://mlsanity.com/paper/2012.14961/) (2020)
- [Unsupervised Pathology Detection: A Deep Dive Into the State of the Art](https://mlsanity.com/paper/2303.00609/) (2023)
- [Unsupervised Anomaly Localization with Structural Feature-Autoencoders](https://mlsanity.com/paper/2208.10992/) (2022)
- [Feature robustness and sex differences in medical imaging: a case study in MRI-based Alzheimer's disease detection](https://mlsanity.com/paper/2204.01737/) (2022)

## Built on by (most cited first, 4 of 4)

- [Towards objective and systematic evaluation of bias in artificial intelligence for medical imaging](https://mlsanity.com/paper/2311.02115/) (2023)
- [Denoising Diffusion Models for Anomaly Localization in Medical Images](https://mlsanity.com/paper/2410.23834/) (2024)
- [Critical Appraisal of Fairness Metrics in Clinical Predictive AI](https://mlsanity.com/paper/2506.17035/) (2025)
- [Fairness-aware Anomaly Detection via Fair Projection](https://mlsanity.com/paper/2505.11132/) (2025)

## Abstract (arXiv)

Background: With the ever-increasing amount of medical imaging data, the demand for algorithms to assist clinicians has amplified. Unsupervised anomaly detection (UAD) models promise to aid in the crucial first step of disease detection. While previous studies have thoroughly explored fairness in supervised models in healthcare, for UAD, this has so far been unexplored. Methods: In this study, we evaluated how dataset composition regarding subgroups manifests in disparate performance of UAD models along multiple protected variables on three large-scale publicly available chest X-ray datasets. Our experiments were validated using two state-of-the-art UAD models for medical images. Finally, we introduced a novel subgroup-AUROC (sAUROC) metric, which aids in quantifying fairness in machine learning. Findings: Our experiments revealed empirical "fairness laws" (similar to "scaling laws" for Transformers) for training-dataset composition: Linear relationships between anomaly detection performance within a subpopulation and its representation in the training data. Our study further revealed performance disparities, even in the case of balanced training data, and compound effects that exacerbate the drop in performance for subjects associated with multiple adversely affected groups. Interpretation: Our study quantified the disparate performance of UAD models against certain demographic subgroups. Importantly, we showed that this unfairness cannot be mitigated by balanced representation alone. Instead, the representation of some subgroups seems harder to learn by UAD models than that of others. The empirical fairness laws discovered in our study make disparate performance in UAD models easier to estimate and aid in determining the most desirable dataset composition.