mlsanityData to 7 Oct 2026

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

arXiv 1606.03657 ↗First posted 12 Jun 2016cs.LG stat.MLcited by 858

Not on the map. Why?

Cited by 44 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that also maximizes the mutual information between a small subset of the latent variables and the observation. We derive a lower bound to the mutual information objective that can be optimized efficiently, and show that our training procedure can be interpreted as a variation of the Wake-Sleep algorithm. Specifically, InfoGAN successfully disentangles writing styles from digit shapes on the MNIST dataset, pose from lighting of 3D rendered images, and background digits from the central digit on the SVHN dataset. It also discovers visual concepts that include hair styles, presence/absence of eyeglasses, and emotions on the CelebA face dataset. Experiments show that InfoGAN learns interpretable representations that are competitive with representations learned by existing fully supervised methods.

Key facts. Cited by 858 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 6; 2020: 4; 2021: 250; 2022: 213; 2023: 149; 2024: 94; 2025: 84; 2026: 57.

858 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2022Toy Models of Superpositioncited by 928
  3. 2021Domain Generalization: A Surveycited by 760
  4. 2024Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Modelscited by 412
  5. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  6. 2023Finding Neurons in a Haystack: Case Studies with Sparse Probingcited by 328
  7. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 301
  8. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  9. 2019Causal Confusion in Imitation Learningcited by 286
  10. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  11. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 221
  12. 2023Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Modelscited by 218
38 more
  1. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equationscited by 172
  2. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  3. 2024Improving Dictionary Learning with Gated Sparse Autoencoderscited by 171
  4. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  5. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Modelscited by 154
  6. 2021Illiterate DALL-E Learns to Composecited by 147
  7. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  8. 2019Imitation Learning as f-Divergence Minimizationcited by 121
  9. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  10. 2022Uncovering the Disentanglement Capability in Text-to-Image Diffusion Modelscited by 116
  11. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  12. 2021Counterfactual Generative Networkscited by 111
  13. 2022Disentangled Representation Learningcited by 111
  14. 2021Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoderscited by 109
  15. 20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
  16. 2023End-to-End Diffusion Latent Optimization Improves Classifier Guidancecited by 107
  17. 2021Deep Generative Models in Engineering Design: A Reviewcited by 103
  18. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  19. 2022Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesiscited by 93
  20. 2021Repurposing GANs for One-shot Semantic Part Segmentationcited by 88
  21. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  22. 2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
  23. 2021Deep Learning for Chest X-ray Analysis: A Surveycited by 84
  24. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  25. 2022Deep Clustering: A Comprehensive Surveycited by 78
  26. 2023SODA: Bottleneck Diffusion Models for Representation Learningcited by 76
  27. 2021FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoderscited by 75
  28. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  29. 2022Causal Machine Learning for Healthcare and Precision Medicinecited by 68
  30. 2022Synthetic Data -- what, why and how?cited by 66
  31. 2021CoNeRF: Controllable Neural Radiance Fieldscited by 65
  32. 2021Controllable and Compositional Generation with Latent-Space Energy-Based Modelscited by 64
  33. 2021Playable Video Generationcited by 63
  34. 2022ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognitioncited by 63
  35. 2022Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Featurescited by 63
  36. 2021DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Datacited by 62
  37. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  38. 2022Factorizing Knowledge in Neural Networkscited by 59

50 most cited of 858 All 858 (JSON)