Oct 19 – 23, 2020
Europe/Zurich timezone

Active Anomaly Detection for time-domain discoveries

Oct 23, 2020, 2:20 PM
Regular talk 9 ML for astroparticle Workshop




We present the first application of adaptive machine learning to the identification of anomalies in a data set of non-periodic time series. The method follows an active learning strategy where highly informative objects are selected to be labelled. This new information is subsequently used to improve the machine learning model, allowing its accuracy to evolve with the addition of human feedback. For the case of anomaly detection, the algorithm aims to maximize the number of real anomalies presented to the expert by slightly modifying the decision boundary of a traditional isolation forest in each iteration. As a proof of concept, we apply the Active Anomaly Discovery (AAD) algorithm to light curves from the Open Supernova Catalog and compare its results to those of a static Isolation Forest (IF). For both methods, we visually inspected objects within 2% highest anomaly scores. We show that AAD was able to identify ∼ 80% more true anomalies than IF. This result is the first evidence that AAD algorithms can play a central role in the search for new physics in complex datasets.

Primary authors

Emille Eugenia DE OLIVEIRA ISHIDA (CNRS) Dr Matwey Kornilov (Moscow State University) Dr Konstantin Malanchev (Moscow State University) Dr Maria Pruzhinskaya (Moscow State University) Dr Vladmir Korolev (Moscow Institute of Physics and Technology)


Dr Alina Volnova (Space Research Institute of the Russian Academy of Sciences) Mr Florian Mondon (LPC - Clermont) Mrs Sreevarsha Sreejith (LPC - Clermont) Dr Anastasia Malancheva (Cinimex) Dr Shubhomoy Das (Washington State University)

Presentation materials