In Search of the Unknown Unknowns: A Multi-Metric Distance Ensemble for Out of Distribution Anomaly Detection in Astronomical Surveys

TL;DR

The paper introduces DiMMAD, a multi-metric ensemble method for out-of-distribution anomaly detection in astronomical data, improving the discovery of new classes by overcoming the limitations of single-metric approaches.

Contribution

It proposes a novel ensemble of distance metrics for anomaly detection, enhancing out-of-distribution detection and interpretability in high-dimensional astronomical datasets.

Findings

DiMMAD outperforms state-of-the-art methods in discovering new classes.

It effectively detects out-of-distribution anomalies in astronomical surveys.

The method maintains competitive performance in rare in-distribution anomaly detection.

Abstract

Distance-based methods involve the computation of distance values between features and are a well-established paradigm in machine learning. In anomaly detection, anomalies are identified by their large distance from normal data points. However, the performance of these methods often hinges on a single, user-selected distance metric (e.g., Euclidean), which may not be optimal for the complex, high-dimensional feature spaces common in astronomy. Here, we introduce a novel anomaly detection method, Distance Multi-Metric Anomaly Detection (DiMMAD), which uses an ensemble of distance metrics to find novelties. Using multiple distance metrics is effectively equivalent to using different geometries in the feature space. By using a robust ensemble of diverse distance metrics, we overcome the metric-selection problem, creating an anomaly score that is not reliant on any single definition of distance. We demonstrate this multi-metric approach as a tool for simple, interpretable scientific discovery on astronomical time series -- (1) with simulated data for the upcoming Vera C. Rubin Observatory Legacy Survey of Space and Time, and (2) real data from the Zwicky Transient Facility. We find that DiMMAD excels at out-of-distribution anomaly detection -- anomalies in the data that might be new classes -- and beats other state-of-the-art methods in the goal of maximizing the diversity of new classes discovered. For rare in-distribution anomaly detection, DiMMAD performs similarly to other methods, but may allow for improved interpretability. All our code is open source: DiMMAD is implemented within DistClassiPy: https://github.com/sidchaini/distclassipy/, while all code to reproduce the results of this paper is available here: https://github.com/sidchaini/dimmad/.