mlsanityData to 14 Oct 2026

Beyond Individual Input for Deep Anomaly Detection on Tabular Data

arXiv 2305.15121 ↗First posted 24 May 2023cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Anomaly detection is vital in many domains, such as finance, healthcare, and cybersecurity. In this paper, we propose a novel deep anomaly detection method for tabular data that leverages Non-Parametric Transformers (NPTs), a model initially proposed for supervised tasks, to capture both feature-feature and sample-sample dependencies. In a reconstruction-based framework, we train an NPT to reconstruct masked features of normal samples. In a non-parametric fashion, we leverage the whole training set during inference and use the model's ability to reconstruct the masked features to generate an anomaly score. To the best of our knowledge, this is the first work to successfully combine feature-feature and sample-sample dependencies for anomaly detection on tabular datasets. Through extensive experiments on 31 benchmark tabular datasets, we demonstrate that our method achieves state-of-the-art performance, outperforming existing methods by 2.4% and 1.2% in terms of F1-score and AUROC, respectively. Our ablation study further proves that modeling both types of dependencies is crucial for anomaly detection on tabular data.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 33 of its 62 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

33 of 62 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2016Layer Normalizationcited by 5,669
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  6. 2018Image Transformercited by 772
  7. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  8. 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 674
  9. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  10. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  11. 2021Tabular Data: Deep Learning is Not All You Needcited by 535
  12. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
21 more
  1. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 336
  2. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 319
  3. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  4. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  5. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 224
  6. 2020Classification-Based Anomaly Detection for General Datacited by 211
  7. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  8. 2020COPOD: Copula-Based Outlier Detectioncited by 146
  9. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  10. 2020Explainable Deep One-Class Classificationcited by 127
  11. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  12. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  13. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  14. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  15. 2019A Mutual Information Maximization Perspective of Language Representation Learningcited by 85
  16. 2018Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoderscited by 83
  17. 2018Extended Isolation Forestcited by 81
  18. 2023TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specializationcited by 32
  19. 2020Simple and Effective Prevention of Mode Collapse in Deep One-Class Classificationcited by 17
  20. 2022TracInAD: Measuring Influence for Anomaly Detectioncited by 8
  21. 2020Transformation Based Deep Anomaly Detection in Astronomical Imagescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 10.

16 papers.

Sort:

By area:

  1. 2024T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Datacited by 14
  2. 2024Retrieval Augmented Deep Anomaly Detection for Tabular Datacited by 6
  3. 2026Towards One-for-All Anomaly Detection for Tabular Datacited by 6
  4. 2026MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detectioncited by 5
  5. 2026Towards Anomaly Detection on Relational Datacited by 5
  6. 2023Comparative Evaluation of Anomaly Detection Methods for Fraud Detection in Online Credit Card Paymentscited by 4
  7. 2025ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detectioncited by 3
  8. 2025LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesiscited by 1
  9. 2026uLEAD-TabPFN: Uncertainty-aware Dependency-based Anomaly Detection with TabPFNcited by 1
  10. 2025Investigating Mask-aware Prototype Learning for Tabular Anomaly Detectioncited by 0
  11. 2026Why the Counterintuitive Phenomenon of Likelihood Rarely Appears in Tabular Anomaly Detection with Deep Generative Models?cited by 0
  12. 2026Masked Diffusion Modeling for Anomaly Detectioncited by 0
4 more
  1. 2026CORE: In-Context Reconstruction for Unified Tabular Anomaly Detectioncited by 0
  2. 2026Revisiting Energy-based Tabular Anomaly Detection: Energy and Reconstruction are Complementarycited by 0
  3. 2026When Identical Rows Disagree: From Benchmark Identifiability to Replication-Robust Anomaly Detectioncited by 0
  4. 2026Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularizationcited by 0