mlsanityData to 14 Oct 2026

Unsupervised Anomaly Detection Using Flow Matching on Tabular Data

arXiv 2608.19801 ↗First posted 20 Aug 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Financial anomaly detection often relies on large unlabeled transaction logs, where anomalous samples may already be present during training. Such training-set contamination violates the clean-normal data assumption underlying many anomaly detection methods. Although flow matching has demonstrated strong performance in generative modeling, its robustness in unsupervised tabular anomaly detection remains underexplored. In this work, we study flow-matching-based anomaly detection under contaminated training data by comparing Time-Conditioned Contraction Matching (TCCM) with Forest-Flow and evaluating multiple anomaly scoring functions. Our results show that the choice of anomaly score is critical. The original single-step Decision score used by TCCM is sensitive to contamination, whereas trajectory-based Deviation and Reconstruction scores provide more stable anomaly signals. With these scores, Forest-Flow becomes competitive with, and in some cases outperforms, TCCM. These findings highlight the importance of anomaly scoring for flow-matching methods in financial anomaly detection under severe class imbalance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 20 Aug 2026.

Builds on

18 of 31 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  5. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  6. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  7. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  8. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  9. 2023Minimizing Trajectory Curvature of ODE-based Generative Modelscited by 89
  10. 2023On Diffusion Modeling for Anomaly Detectioncited by 72
  11. 2018Generative Adversarial Active Learning for Unsupervised Outlier Detectioncited by 65
  12. 2023Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Treescited by 62
6 more
  1. 2024A Closer Look at AUROC and AUPRC under Class Imbalancecited by 57
  2. 2019Unsupervised Representation Learning by Predicting Random Distancescited by 35
  3. 2022Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solutioncited by 24
  4. 2020OneFlow: One-class flow for anomaly detection based on a minimal volume regioncited by 9
  5. 2025Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matchingcited by 9
  6. 2024EntropyStop: Unsupervised Deep Outlier Detection with Loss Entropycited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning Unified Representations of Normalcy for Time Series Anomaly Detection
  2. 2026Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection
  3. 2026Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
  4. 2024Anomaly Detection of Tabular Data Using LLMs
  5. 2024Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detection
  6. 2026MATCH: Flow Matching for Multi-View Anomaly Detection
  7. 2026Graph-Spectral Flow Matching for Multivariate Time Series Anomaly Detection
  8. 2023TabADM: Unsupervised Tabular Anomaly Detection with Diffusion Models