mlsanityData to 14 Oct 2026

ADGym: Design Choices for Deep Anomaly Detection

arXiv 2309.15376 ↗First posted 27 Sep 2023cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 37 of its 89 references that are in the map. First posted on arXiv 27 Sep 2023.

Builds on

37 of 89 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  7. 2016An overview of gradient descent optimization algorithmscited by 1,033
  8. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  9. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  10. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  11. 2021A Survey of Data Augmentation Approaches for NLPcited by 409
  12. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 305
25 more
  1. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  2. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  3. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 226
  4. 2020Design Space for Graph Neural Networkscited by 182
  5. 2019Deep Anomaly Detection with Deviation Networkscited by 153
  6. 2022ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functionscited by 153
  7. 2020COPOD: Copula-Based Outlier Detectioncited by 146
  8. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  9. 2018Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detectioncited by 79
  10. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  11. 2019Deep Weakly-supervised Anomaly Detectioncited by 59
  12. 2020RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networkscited by 55
  13. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  14. 2021Feature Encoding with AutoEncoders for Weakly-supervised Anomaly Detectioncited by 42
  15. 2020TODS: An Automated Time Series Outlier Detection Systemcited by 41
  16. 2019Dataset2Vec: Learning Dataset Meta-Featurescited by 38
  17. 2020Benchmarking Unsupervised Outlier Detection with Realistic Synthetic Datacited by 25
  18. 2021CloudRCA: A Root Cause Analysis Framework for Cloud Computing Platformscited by 24
  19. 2023Weakly Supervised Anomaly Detection: A Surveycited by 22
  20. 2020PyODDS: An End-to-end Outlier Detection System with Automated Machine Learningcited by 21
  21. 2022Toward Unsupervised Outlier Model Selectioncited by 19
  22. 2021An Information Retrieval Approach to Building Datasets for Hate Speech Detectioncited by 9
  23. 2022FedTADBench: Federated Time-Series Anomaly Detection Benchmarkcited by 6
  24. 2023Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networkscited by 5
  25. 2023Neural Architecture Search for Visual Anomaly Segmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 5; 2026: 2.

11 papers.

  1. 2024AD-LLM: Benchmarking Large Language Models for Anomaly Detectioncited by 26
  2. 2024Generative Semi-supervised Graph Anomaly Detectioncited by 22
  3. 2024MetaOOD: Automatic Selection of OOD Detection Modelscited by 16
  4. 2025ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Modelscited by 9
  5. 2025M3OOD: Automatic Selection of Multimodal OOD Detectorscited by 5
  6. 2025We Need to Rethink Benchmarking in Anomaly Detectioncited by 4
  7. 2024Multi-Normal Prototypes Learning for Weakly Supervised Anomaly Detectioncited by 1
  8. 2026Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuningcited by 1
  9. 2025Position: Untrained Machine Learning for Anomaly Detection by using 3D Point Cloud Datacited by 0
  10. 2025TSGym: Design Choices for Deep Multivariate Time-Series Forecastingcited by 0
  11. 2026RGLD: Randomized Global-Local Density Estimation for Tabular Anomaly Detectioncited by 0