# Bidirectional Conditional Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1711.07461 · HTML: https://mlsanity.com/paper/1711.07461/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2017.

## Built on by (most cited first, 10 of 10)

- [Counterfactual (Non-)identifiability of Learned Structural Causal Models](https://mlsanity.com/paper/2301.09031/) (2023)
- [CAT: Controllable Attribute Translation for Fair Facial Attribute Classification](https://mlsanity.com/paper/2209.06850/) (2022)
- [Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning](https://mlsanity.com/paper/2112.03803/) (2021)
- [Counterfactual Reasoning Using Predicted Latent Personality Dimensions for Optimizing Persuasion Outcome](https://mlsanity.com/paper/2404.13792/) (2024)
- [Causal Discovery and Counterfactual Reasoning to Optimize Persuasive Dialogue Policies](https://mlsanity.com/paper/2503.16544/) (2025)
- [Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge](https://mlsanity.com/paper/2504.13904/) (2025)
- [Stein Latent Optimization for Generative Adversarial Networks](https://mlsanity.com/paper/2106.05319/) (2021)
- [Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance](https://mlsanity.com/paper/2210.13507/) (2022)
- [Boltzmann Tuning of Generative Models](https://mlsanity.com/paper/2104.05252/) (2021)
- [CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning](https://mlsanity.com/paper/2512.09368/) (2025)

## Abstract (arXiv)

Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples (x) conditioned on both latent variables (z) and known auxiliary information (c). We propose the Bidirectional cGAN (BiCoGAN), which effectively disentangles z and c in the generation process and provides an encoder that learns inverse mappings from x to both z and c, trained jointly with the generator and the discriminator. We present crucial techniques for training BiCoGANs, which involve an extrinsic factor loss along with an associated dynamically-tuned importance weight. As compared to other encoder-based cGANs, BiCoGANs encode c more accurately, and utilize z and c more effectively and in a more disentangled way to generate samples.