mlsanityData to 14 Oct 2026

Semi-Supervised Learning with Normalizing Flows

arXiv 1912.13025 ↗First posted 30 Dec 2019cs.LG stat.MLcited by 76

Not on the map. Why?

Abstract (arXiv)

Normalizing flows transform a latent distribution through an invertible neural network for a flexible and pleasingly simple approach to generative modelling, while preserving an exact likelihood. We propose FlowGMM, an end-to-end approach to generative semi supervised learning with normalizing flows, using a latent Gaussian mixture model. FlowGMM is distinct in its simplicity, unified treatment of labelled and unlabelled data with an exact likelihood, interpretability, and broad applicability beyond image data. We show promising results on a wide range of applications, including AG-News and Yahoo Answers text data, tabular data, and semi-supervised image classification. We also show that FlowGMM can discover interpretable structure, provide real-time optimization-free feature visualizations, and specify well calibrated predictive distributions.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 23; 2023: 12; 2024: 9; 2025: 12; 2026: 8.

76 papers.

Sort:

By area:

  1. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  2. 2021DOC2PPT: Automatic Presentation Slides Generation from Scientific Documentscited by 70
  3. 2022Verifying the Union of Manifolds Hypothesis for Image Datacited by 64
  4. 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 60
  5. 2021Resampling Base Distributions of Normalizing Flowscited by 42
  6. 2022Universal approximation property of invertible neural networkscited by 30
  7. 2021ECINN: Efficient Counterfactuals from Invertible Neural Networkscited by 26
  8. 2022Constructing Balance from Imbalance for Long-tailed Image Recognitioncited by 25
  9. 2022Detecting Multivariate Time Series Anomalies with Zero Known Labelcited by 21
  10. 2023On Sampling with Approximate Transport Mapscited by 21
  11. 2021On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competitioncited by 18
  12. 2022Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Modelcited by 18
38 more
  1. 2022Chroma-VAE: Mitigating Shortcut Learning with Generative Classifierscited by 17
  2. 2021Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstructioncited by 16
  3. 2021Task-agnostic Continual Learning with Hybrid Probabilistic Modelscited by 16
  4. 2021On the expressivity of bi-Lipschitz normalizing flowscited by 16
  5. 2024Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentationcited by 16
  6. 2025PreGenie: An Agentic Framework for High-quality Visual Presentation Generationcited by 16
  7. 2023Label-Free Multivariate Time Series Anomaly Detectioncited by 14
  8. 2023A Review of Change of Variable Formulas for Generative Modelingcited by 13
  9. 2021LiftPool: Bidirectional ConvNet Poolingcited by 11
  10. 2022Gradual Domain Adaptation via Normalizing Flowscited by 11
  11. 2021Differentially Private Normalizing Flows for Privacy-Preserving Density Estimationcited by 10
  12. 2022Towards Accurate Open-Set Recognition via Background-Class Regularizationcited by 10
  13. 2025Designing a Conditional Prior Distribution for Flow-Based Generative Modelscited by 10
  14. 2023CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flowscited by 8
  15. 2022Class-Imbalanced Complementary-Label Learning via Weighted Losscited by 7
  16. 2023Normalizing flow sampling with Langevin dynamics in the latent spacecited by 7
  17. 2022Improving VAE-based Representation Learningcited by 6
  18. 2023Coupled Variational Autoencodercited by 6
  19. 2024MGF: Mixed Gaussian Flow for Diverse Trajectory Predictioncited by 6
  20. 2023GC-Flow: A Graph-Based Flow Network for Effective Clusteringcited by 5
  21. 2024Treeffuser: Probabilistic Predictions via Conditional Diffusions with Gradient-Boosted Treescited by 5
  22. 2021Input Invex Neural Networkcited by 4
  23. 2022Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variationcited by 4
  24. 2022StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfercited by 4
  25. 2025Evaluating multiple models using labeled and unlabeled datacited by 4
  26. 2022AdaAnn: Adaptive Annealing Scheduler for Probability Density Approximationcited by 3
  27. 2022Text to Image Synthesis using Stacked Conditional Variational Autoencoders and Conditional Generative Adversarial Networkscited by 3
  28. 2024ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encodingcited by 3
  29. 2024This Probably Looks Exactly Like That: An Invertible Prototypical Networkcited by 3
  30. 2025Learning Geometry and Topology via Multi-Chart Flowscited by 3
  31. 2022Universality of parametric Coupling Flows over parametric diffeomorphismscited by 2
  32. 2022Exploiting Unlabeled Data for Target-Oriented Opinion Words Extractioncited by 2
  33. 2023On the Approximation of Bi-Lipschitz Maps by Invertible Neural Networkscited by 2
  34. 2024Learning from Reduced Labels for Long-Tailed Datacited by 2
  35. 2024Generative vs. Discriminative modeling under the lens of uncertainty quantificationcited by 2
  36. 2021Semi-supervised Learning with Missing Values Imputationcited by 1
  37. 2022A Deep Learning Approach to Probabilistic Forecasting of Weathercited by 1
  38. 2022Training Normalizing Flows from Dependent Datacited by 1

50 most cited of 76 All 76 (JSON)