"Flux+Mutability": A Conditional Generative Approach to One-Class Classification and Anomaly Detection

04/19/2022
by   C. Fanelli, et al.
1

Anomaly Detection is becoming increasingly popular within the experimental physics community. At experiments such as the Large Hadron Collider, anomaly detection is at the forefront of finding new physics beyond the Standard Model. This paper details the implementation of a novel Machine Learning architecture, called Flux+Mutability, which combines cutting-edge conditional generative models with clustering algorithms. In the `flux' stage we learn the distribution of a reference class. The `mutability' stage at inference addresses if data significantly deviates from the reference class. We demonstrate the validity of our approach and its connection to multiple problems spanning from one-class classification to anomaly detection. In particular, we apply our method to the isolation of neutral showers in an electromagnetic calorimeter and show its performance in detecting anomalous dijets events from standard QCD background. This approach limits assumptions on the reference sample and remains agnostic to the complementary class of objects of a given problem. We describe the possibility of dynamically generating a reference population and defining selection criteria via quantile cuts. Remarkably this flexible architecture can be deployed for a wide range of problems, and applications like multi-class classification or data quality control are left for further exploration.

READ FULL TEXT

page 13

page 16

page 24

page 25

research
06/14/2019

(1 + ε)-class Classification: an Anomaly Detection Method for Highly Imbalanced or Incomplete Data Sets

Anomaly detection is not an easy problem since distribution of anomalous...
research
12/20/2022

Resonant Anomaly Detection with Multiple Reference Datasets

An important class of techniques for resonant anomaly detection in high ...
research
02/15/2021

Multi-class Classification Based Anomaly Detection of Insider Activities

Insider threats are the cyber attacks from within the trusted entities o...
research
11/07/2016

One Class Splitting Criteria for Random Forests

Random Forests (RFs) are strong machine learning tools for classificatio...
research
01/25/2023

Unravelling physics beyond the standard model with classical and quantum anomaly detection

Much hope for finding new physics phenomena at microscopic scale relies ...
research
08/09/2014

One-Class Support Measure Machines for Group Anomaly Detection

We propose one-class support measure machines (OCSMMs) for group anomaly...
research
12/23/2022

Anomaly Detection using Ensemble Classification and Evidence Theory

Multi-class ensemble classification remains a popular focus of investiga...

Please sign up or login with your details

Forgot password? Click here to reset