mlsanityData to 14 Oct 2026

GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution

arXiv 1611.04051 ↗First posted 12 Nov 2016stat.ML cs.LGcited by 48

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GAN) have limitations when the goal is to generate sequences of discrete elements. The reason for this is that samples from a distribution on discrete objects such as the multinomial are not differentiable with respect to the distribution parameters. This problem can be avoided by using the Gumbel-softmax distribution, which is a continuous approximation to a multinomial distribution parameterized in terms of the softmax function. In this work, we evaluate the performance of GANs based on recurrent neural networks with Gumbel-softmax output distributions in the task of generating sequences of discrete elements.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 17; 2023: 5; 2024: 5; 2025: 6; 2026: 2.

48 papers.

Sort:

By area:

  1. 2021A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learningcited by 82
  2. 2024Discrete-state Continuous-time Diffusion for Graph Generationcited by 76
  3. 2022Eco2AI: carbon emissions tracking of machine learning models as the first step towards sustainable AIcited by 58
  4. 2021Math Word Problem Generation with Mathematical Consistency and Problem Context Constraintscited by 27
  5. 2022Musika! Fast Infinite Waveform Music Generationcited by 24
  6. 2022A survey on text generation using generative adversarial networkscited by 16
  7. 2022Data Imputation with Iterative Graph Reconstructioncited by 15
  8. 2021Semantic Palette: Guiding Scene Generation with Class Proportionscited by 14
  9. 2021A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensingcited by 13
  10. 2023Efficient Generator of Mathematical Expressions for Symbolic Regressioncited by 13
  11. 2022Generating music with sentiment using Transformer-GANscited by 11
  12. 2024Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decodingcited by 10
36 more
  1. 2021SUPR-GAN: SUrgical PRediction GAN for Event Anticipation in Laparoscopic and Robotic Surgerycited by 7
  2. 2023Improved Training of Mixture-of-Experts Language GANscited by 7
  3. 2025V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generationcited by 6
  4. 2025Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddingscited by 6
  5. 2021Generating Symbolic Reasoning Problems with Transformer GANscited by 5
  6. 2022The Power of Fragmentation: A Hierarchical Transformer Model for Structural Segmentation in Symbolic Music Generationcited by 5
  7. 2022Predicting Opinion Dynamics via Sociologically-Informed Neural Networkscited by 5
  8. 2021Categorical EHR Imputation with Generative Adversarial Netscited by 4
  9. 2023Revisiting the Gumbel-Softmax in MADDPGcited by 3
  10. 2021Adversarial Machine Learning in Text Analysis and Generationcited by 2
  11. 2021Emojich -- zero-shot emoji generation using Russian language: a technical reportcited by 2
  12. 2021Improvement in Machine Translation with Generative Adversarial Networkscited by 1
  13. 2021Survey of Generative Methods for Social Media Analysiscited by 1
  14. 2022FinGAN: Generative Adversarial Network for Analytical Customer Relationship Management in Banking and Insurancecited by 1
  15. 2022Why GANs are overkill for NLPcited by 1
  16. 2022AdaTriplet-RA: Domain Matching via Adaptive Triplet and Reinforced Attention for Unsupervised Domain Adaptationcited by 1
  17. 2022A Mutation-based Text Generation for Adversarial Machine Learning Applicationscited by 1
  18. 2022Modified Query Expansion Through Generative Adversarial Networks for Information Extraction in E-Commercecited by 1
  19. 2023Learning a Consensus Sub-Network with Polarization Regularization and One Pass Trainingcited by 1
  20. 2023Data-Free Distillation of Language Model by Text-to-Text Transfercited by 1
  21. 2025Bringing Emerging Architectures to Sequence Labeling in NLPcited by 1
  22. 2021Generating Multi-type Temporal Sequences to Mitigate Class-imbalanced Problemcited by 0
  23. 2021OptAGAN: Entropy-based finetuning on text VAE-GANcited by 0
  24. 2022Gradient-Based Learning of Discrete Structured Measurement Operators for Signal Recoverycited by 0
  25. 2022Dynamics of Fourier Modes in Torus Generative Adversarial Networkscited by 0
  26. 2022Bridging Music and Text with Crowdsourced Music Comments: A Sequence-to-Sequence Framework for Thematic Music Comments Generationcited by 0
  27. 2022Sample-efficient Quantum Born Machine through Coding Rate Reductioncited by 0
  28. 2022Knowledge Graph Quality Evaluation under Incomplete Informationcited by 0
  29. 2024Deep autoregressive modeling for land use land covercited by 0
  30. 2024Forging the Forger: An Attempt to Improve Authorship Verification via Data Augmentationcited by 0
  31. 2024DogLayout: Denoising Diffusion GAN for Discrete and Continuous Layout Generationcited by 0
  32. 2025Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learningcited by 0
  33. 2025Deep Generative Models for Discrete Genotype Simulationcited by 0
  34. 2026FlexAct: Why Learn when you can Pick?cited by 0
  35. 2025GRADE: Replacing Policy Gradients with Backpropagation for LLM Alignmentcited by 0
  36. 2026Sufficiently Reduced Distributional Regressioncited by 0