# ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching

arXiv: https://arxiv.org/abs/1709.01215 · HTML: https://mlsanity.com/paper/1709.01215/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2017.

## Built on by (most cited first, 30 of 32)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Diffusion-GAN: Training GANs with Diffusion](https://mlsanity.com/paper/2206.02262/) (2022)
- [LAFITE: Towards Language-Free Training for Text-to-Image Generation](https://mlsanity.com/paper/2111.13792/) (2021)
- [D2C: Diffusion-Denoising Models for Few-shot Conditional Generation](https://mlsanity.com/paper/2106.06819/) (2021)
- [Dual Contrastive Learning for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2104.07689/) (2021)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Counterfactual Identifiability of Bijective Causal Models](https://mlsanity.com/paper/2302.02228/) (2023)
- [SoK: Privacy-Preserving Data Synthesis](https://mlsanity.com/paper/2307.02106/) (2023)
- [DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation](https://mlsanity.com/paper/2103.11109/) (2021)
- [Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions](https://mlsanity.com/paper/2210.16222/) (2022)
- [Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences](https://mlsanity.com/paper/2506.02095/) (2025)
- [Anomaly Detection by Leveraging Incomplete Anomalous Knowledge with Anomaly-Aware Bidirectional GANs](https://mlsanity.com/paper/2204.13335/) (2022)
- [Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding](https://mlsanity.com/paper/2402.19009/) (2024)
- [Dual Projection Generative Adversarial Networks for Conditional Image Generation](https://mlsanity.com/paper/2108.09016/) (2021)
- [Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data](https://mlsanity.com/paper/2109.08311/) (2021)
- [Bi-level Doubly Variational Learning for Energy-based Latent Variable Models](https://mlsanity.com/paper/2203.14702/) (2022)
- [Hyperbolic Generative Adversarial Network](https://mlsanity.com/paper/2102.05567/) (2021)
- [Discriminative-Generative Representation Learning for One-Class Anomaly Detection](https://mlsanity.com/paper/2107.12753/) (2021)
- [Multimodal Adversarially Learned Inference with Factorized Discriminators](https://mlsanity.com/paper/2112.10384/) (2021)
- [Reconstruct Face from Features Using GAN Generator as a Distribution Constraint](https://mlsanity.com/paper/2206.04295/) (2022)
- [Worst-Case Morphs using Wasserstein ALI and Improved MIPGAN](https://mlsanity.com/paper/2310.08371/) (2023)
- [LensCraft: Your Professional Virtual Cinematographer](https://mlsanity.com/paper/2506.00988/) (2025)
- [IGAN: Inferent and Generative Adversarial Networks](https://mlsanity.com/paper/2109.13360/) (2021)
- [Spot The Odd One Out: Regularized Complete Cycle Consistent Anomaly Detector GAN](https://mlsanity.com/paper/2304.07769/) (2023)
- [Fast Ensemble Learning Using Adversarially-Generated Restricted Boltzmann Machines](https://mlsanity.com/paper/2101.01042/) (2021)
- [Symmetric Wasserstein Autoencoders](https://mlsanity.com/paper/2106.13024/) (2021)
- [Independent Encoder for Deep Hierarchical Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2107.02494/) (2021)
- [Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matching](https://mlsanity.com/paper/2107.08792/) (2021)
- [Semi-Supervised Image-to-Image Translation using Latent Space Mapping](https://mlsanity.com/paper/2203.15241/) (2022)
- [A Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Vision](https://mlsanity.com/paper/2311.00995/) (2023)

## Abstract (arXiv)

We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We unify a broad family of adversarial models as joint distribution matching problems. Our approach stabilizes learning of unsupervised bidirectional adversarial learning methods. Further, we introduce an extension for semi-supervised learning tasks. Theoretical results are validated in synthetic data and real-world applications.