# Semi-Conditional Normalizing Flows for Semi-Supervised Learning

arXiv: https://arxiv.org/abs/1905.00505 · HTML: https://mlsanity.com/paper/1905.00505/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2019.

## Built on by (most cited first, 15 of 15)

- [Task-agnostic Continual Learning with Hybrid Probabilistic Models](https://mlsanity.com/paper/2106.12772/) (2021)
- [LiftPool: Bidirectional ConvNet Pooling](https://mlsanity.com/paper/2104.00996/) (2021)
- [Denoising Deep Generative Models](https://mlsanity.com/paper/2212.01265/) (2022)
- [Lagrangian Flow Networks for Conservation Laws](https://mlsanity.com/paper/2305.16846/) (2023)
- [Conditional Matrix Flows for Gaussian Graphical Models](https://mlsanity.com/paper/2306.07255/) (2023)
- [Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics](https://mlsanity.com/paper/2104.04391/) (2021)
- [This Probably Looks Exactly Like That: An Invertible Prototypical Network](https://mlsanity.com/paper/2407.12200/) (2024)
- [Learning Geometry and Topology via Multi-Chart Flows](https://mlsanity.com/paper/2505.24665/) (2025)
- [Generative vs. Discriminative modeling under the lens of uncertainty quantification](https://mlsanity.com/paper/2406.09172/) (2024)
- [Semi-supervised Learning with Missing Values Imputation](https://mlsanity.com/paper/2106.01708/) (2021)
- [Flow Plugin Network for conditional generation](https://mlsanity.com/paper/2110.04081/) (2021)
- [WeaNF: Weak Supervision with Normalizing Flows](https://mlsanity.com/paper/2204.13409/) (2022)
- [Weakly Supervised Label Learning Flows](https://mlsanity.com/paper/2302.09649/) (2023)
- [LoLiSRFlow: Joint Single Image Low-light Enhancement and Super-resolution via Cross-scale Transformer-based Conditional Flow](https://mlsanity.com/paper/2402.18871/) (2024)
- [Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization](https://mlsanity.com/paper/2410.02628/) (2024)

## Abstract (arXiv)

This paper proposes a semi-conditional normalizing flow model for semi-supervised learning. The model uses both labelled and unlabeled data to learn an explicit model of joint distribution over objects and labels. Semi-conditional architecture of the model allows us to efficiently compute a value and gradients of the marginal likelihood for unlabeled objects. The conditional part of the model is based on a proposed conditional coupling layer. We demonstrate performance of the model for semi-supervised classification problem on different datasets. The model outperforms the baseline approach based on variational auto-encoders on MNIST dataset.