ADBench: Anomaly Detection Benchmark

Advances in Neural Information Processing Systems (NeurIPS), 2022

18 Pages Posted: 6 Dec 2022

See all articles by Songqiao Han

Songqiao Han

affiliation not provided to SSRN

Xiyang Hu

Carnegie Mellon University

Hailiang Huang

Shanghai University of Finance and Economics

Minqi Jiang

affiliation not provided to SSRN

Yue Zhao

Carnegie Mellon University - H. John Heinz III College of Information Systems and Public Policy

Date Written: November 3, 2022

Abstract

Given a long list of anomaly detection algorithms developed in the last few decades, how do they perform with regard to (i) varying levels of supervision, (ii) different types of anomalies, and (iii) noisy and corrupted data? In this work, we answer these key questions by conducting (to our best knowledge) the most comprehensive anomaly detection benchmark with 30 algorithms on 57 benchmark datasets, named ADBench. Our extensive experiments (98,436 in total) identify meaningful insights into the role of supervision and anomaly types, and unlock future directions for researchers in algorithm selection and design. With ADBench, researchers can easily conduct comprehensive and fair evaluations for newly proposed methods on the datasets (including our contributed ones from natural language and computer vision domains) against the existing baselines. To foster accessibility and reproducibility, we fully open-source ADBench and the corresponding results.

Keywords: Anomaly Detection, Outlier Detection

JEL Classification: C00, C14, C44, C53, C61, C8

Suggested Citation

Han, Songqiao and Hu, Xiyang and Huang, Hailiang and Jiang, Minqi and Zhao, Yue, ADBench: Anomaly Detection Benchmark (November 3, 2022). Advances in Neural Information Processing Systems (NeurIPS), 2022, Available at SSRN: https://ssrn.com/abstract=4266498 or http://dx.doi.org/10.2139/ssrn.4266498

Songqiao Han

affiliation not provided to SSRN

Xiyang Hu

Carnegie Mellon University ( email )

Pittsburgh, PA
United States

HOME PAGE: http://www.andrew.cmu.edu/user/xiyanghu/

Hailiang Huang

Shanghai University of Finance and Economics ( email )

777 Guoding Road
Shanghai, AK Shanghai 200433
China

Minqi Jiang (Contact Author)

affiliation not provided to SSRN

Yue Zhao

Carnegie Mellon University - H. John Heinz III College of Information Systems and Public Policy

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
59
Abstract Views
348
Rank
662,734
PlumX Metrics