ADGym: Design Choices for Deep Anomaly Detection

TL;DR

This paper introduces ADGym, a platform for evaluating and automatically selecting key design choices in deep anomaly detection methods, demonstrating that tailored models outperform existing state-of-the-art techniques.

Contribution

ADGym provides a systematic framework to analyze and optimize design choices in deep anomaly detection, filling a gap in understanding their individual impacts.

Findings

Models optimized with ADGym outperform existing methods.

Design choices significantly influence anomaly detection performance.

Automatic selection of design elements improves detection accuracy.

Abstract

Deep learning (DL) techniques have recently found success in anomaly detection (AD) across various fields such as finance, medical services, and cloud computing. However, most of the current research tends to view deep AD algorithms as a whole, without dissecting the contributions of individual design choices like loss functions and network architectures. This view tends to diminish the value of preliminary steps like data preprocessing, as more attention is given to newly designed loss functions, network architectures, and learning paradigms. In this paper, we aim to bridge this gap by asking two key questions: (i) Which design choices in deep AD methods are crucial for detecting anomalies? (ii) How can we automatically select the optimal design choices for a given AD dataset, instead of relying on generic, pre-existing solutions? To address these questions, we introduce ADGym, a platform specifically crafted for comprehensive evaluation and automatic selection of AD design elements in deep methods. Our extensive experiments reveal that relying solely on existing leading methods is not sufficient. In contrast, models developed using ADGym significantly surpass current state-of-the-art techniques.