mlsanityData to 13 Oct 2026

Adversarial Feature Matching for Text Generation

arXiv 1706.03850 ↗First posted 12 Jun 2017stat.ML cs.CL cs.LGcited by 58

Not on the map. Why?

Abstract (arXiv)

The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We propose a framework for generating realistic text via adversarial training. We employ a long short-term memory network as generator, and a convolutional network as discriminator. Instead of using the standard objective of GAN, we propose matching the high-dimensional latent feature distributions of real and synthetic sentences, via a kernelized discrepancy metric. This eases adversarial training by alleviating the mode-collapsing problem. Our experiments show superior performance in quantitative evaluation, and demonstrate that our model can generate realistic-looking sentences.

Key facts. Cited by 58 papers in the map (data through 13 Oct 2026). First posted on arXiv 12 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2020: 1; 2021: 18; 2022: 8; 2023: 14; 2024: 6; 2025: 7; 2026: 4.

58 papers.

Sort:

By area:

  1. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  2. 2023On the Creativity of Large Language Modelscited by 57
  3. 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Modelcited by 56
  4. 2021Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastingscited by 37
  5. 2025POSTA: A Go-to Framework for Customized Artistic Poster Generationcited by 36
  6. 2023Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Gamecited by 27
  7. 2021Creativity and Machine Learning: A Surveycited by 21
  8. 2024DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillationcited by 20
  9. 2022The Health Gym: Synthetic Health-Related Datasets for the Development of Reinforcement Learning Algorithmscited by 19
  10. 2022A survey on text generation using generative adversarial networkscited by 16
  11. 2021TextBox: A Unified, Modularized, and Extensible Framework for Text Generationcited by 15
  12. 2021Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Reviewcited by 15
38 more
  1. 2023TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformerscited by 13
  2. 2024An improved tabular data generator with VAE-GMM integrationcited by 13
  3. 2022Pretraining Text Encoders with Adversarial Mixture of Training Signal Generatorscited by 9
  4. 2025Generative Video Semantic Communication via Multimodal Semantic Fusion with Large Modelcited by 9
  5. 2023Time-series Generation by Contrastive Imitationcited by 8
  6. 2024A Multi-Faceted Evaluation Framework for Assessing Synthetic Data Generated by Large Language Modelscited by 8
  7. 2021Say What? Collaborative Pop Lyric Generation Using Multitask Transfer Learningcited by 7
  8. 2023Improved Training of Mixture-of-Experts Language GANscited by 7
  9. 2025Better LLM Reasoning via Dual-Playcited by 7
  10. 2023Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systemscited by 6
  11. 2025Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddingscited by 6
  12. 2021Generating Symbolic Reasoning Problems with Transformer GANscited by 5
  13. 2023A Generative Adversarial Network for Climate Tipping Point Discovery (TIP-GAN)cited by 5
  14. 2024Deep Reinforcement Learning for Modelling Protein Complexescited by 5
  15. 2021Conditional Loss and Deep Euler Scheme for Time Series Generationcited by 4
  16. 2021Categorical EHR Imputation with Generative Adversarial Netscited by 4
  17. 2021Regularizing Transformers With Deep Probabilistic Layerscited by 4
  18. 2020Nested-Wasserstein Self-Imitation Learning for Sequence Generationcited by 3
  19. 2022BSDGAN: Balancing Sensor Data Generative Adversarial Networks for Human Activity Recognitioncited by 3
  20. 2023Persona-aware Generative Model for Code-mixed Languagecited by 3
  21. 2021Adversarial Machine Learning in Text Analysis and Generationcited by 2
  22. 2021SparseGAN: Sparse Generative Adversarial Network for Text Generationcited by 2
  23. 2021Textual Data Distributions: Kullback Leibler Textual Distributions Contrasts on GPT-2 Generated Texts, with Supervised, Unsupervised Learning on Vaccine & Market Topics & Sentimentcited by 2
  24. 2021Learning Natural Language Generation from Scratchcited by 2
  25. 2023Revisiting the Gumbel-Softmax in MADDPGcited by 2
  26. 2025C-LEAD: Contrastive Learning for Enhanced Adversarial Defensecited by 2
  27. 2026Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrationscited by 2
  28. 2021Measure-conditional Discriminator with Stationary Optimum for GANs and Statistical Distance Surrogatescited by 1
  29. 2021Text Generation with Deep Variational GANcited by 1
  30. 2021Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphscited by 1
  31. 2021A Deep Generative Model for Reordering Adjacency Matricescited by 1
  32. 2021Survey of Generative Methods for Social Media Analysiscited by 1
  33. 2022InitialGAN: A Language GAN with Completely Random Initializationcited by 1
  34. 2022An Overview on Controllable Text Generation via Variational Auto-Encoderscited by 1
  35. 2023Complex Mathematical Symbol Definition Structures: A Dataset and Model for Coordination Resolution in Definition Extractioncited by 1
  36. 2024Emotion-Guided Image to Music Generationcited by 1
  37. 2026Self-Generative Adversarial Fine-Tuning for Large Language Modelscited by 1
  38. 2022Bridging Music and Text with Crowdsourced Music Comments: A Sequence-to-Sequence Framework for Thematic Music Comments Generationcited by 0

50 most cited of 58 All 58 (JSON)