N-1 Experts: Unsupervised Anomaly Detection Model Selection

Constantin Le Clei, Yasha Pushak, Fatjon Zogaj, Moein Owhadi Kareshk, Zahra Zohrevand, Robert Harlow, Hesam Fathi Moghadam, Sungpack Hong, Hassan Chafi

Abstract: Manually finding the best combination of machine learning training algorithm, model and hyperparameters can be challenging. In supervised settings, this burden has been alleviated with the introduction of automated machine learning (AutoML) methods. However, similar methods are noticeably absent for fully unsupervised applications, such as anomaly detection. We introduce one of the first such methods, N-1 Experts, which we compare to a recent state-of-the-art baseline, MetaOD, and show favourable performance.

Keywords: Anomaly detection, unsupervised model selection, unsupervised CASH

One-sentence Summary: Unsupervised AutoML for anomaly detection that leverages complementary model strengths.

Reproducibility Checklist: Yes

Broader Impact Statement: Yes

Paper Availability And License: Yes

Code Of Conduct: Yes

Reviewers:

Fatjon Zogaj, [e-mail]
Constantin Le Clei, [e-mail]