Signatures to help interpretability of anomalies
Emmanuel Gangler (1), Emille E. O. Ishida (1), Matwey V. Kornilov (2, 3), Vladimir Korolev, Anastasia Lavrukhina (3), Konstantin Malanchev (4), Maria V. Pruzhinskaya (1, 3), Etienne Russeil (1, 5), Timofey Semenikhin (3, 6), Sreevarsha Sreejith (7)
TL;DR
This paper introduces anomaly signatures to improve the interpretability of anomaly detection in machine learning, helping users understand which features contribute to the detection decision.
Contribution
The paper proposes the concept of anomaly signatures as a novel method to enhance interpretability of anomaly detection results.
Findings
Anomaly signatures highlight feature contributions to decisions.
Improved interpretability aids in understanding anomaly detection outputs.
Potential to assist astronomers in analyzing anomalies.
Abstract
Machine learning is often viewed as a black box when it comes to understanding its output, be it a decision or a score. Automatic anomaly detection is no exception to this rule, and quite often the astronomer is left to independently analyze the data in order to understand why a given event is tagged as an anomaly. We introduce here idea of anomaly signature, whose aim is to help the interpretability of anomalies by highlighting which features contributed to the decision.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Anomaly Detection Techniques and Applications · Adversarial Robustness in Machine Learning