mlsanityData to 7 Oct 2026

Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models

arXiv 2201.09644 ↗First posted 24 Jan 2022cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Realistic fine-grained multi-agent simulation of real-world complex systems is crucial for many downstream tasks such as reinforcement learning. Recent work has used generative models (GANs in particular) for providing high-fidelity simulation of real-world systems. However, such generative models are often monolithic and miss out on modeling the interaction in multi-agent systems. In this work, we take a first step towards building multiple interacting generative models (GANs) that reflects the interaction in real world. We build and analyze a hierarchical set-up where a higher-level GAN is conditioned on the output of multiple lower-level GANs. We present a technique of using feedback from the higher-level GAN to improve performance of lower-level GANs. We mathematically characterize the conditions under which our technique is impactful, including understanding the transfer learning nature of our set-up. We present three distinct experiments on synthetic data, time series data, and image domain, revealing the wide applicability of our technique.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 39 references that are in the map. First posted on arXiv 24 Jan 2022.

Builds on

27 of 39 references.

References · 27

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  4. 2017Improved Training of Wasserstein GANscited by 2,223
  5. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  6. 2016Least Squares Generative Adversarial Networkscited by 1,000
  7. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  8. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  9. 2016Coupled Generative Adversarial Networkscited by 216
  10. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  11. 2018Multi-Adversarial Domain Adaptationcited by 195
  12. 2018Transferring GANs: generating images from limited datacited by 134
15 more
  1. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  2. 2020Few-shot Image Generation with Elastic Weight Consolidationcited by 122
  3. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  4. 2019Image Generation From Small Datasets via Batch Statistics Adaptationcited by 102
  5. 2020FedGAN: Federated Generative Adversarial Networks for Distributed Datacited by 89
  6. 2018Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learningcited by 80
  7. 2020COT-GAN: Generating Sequential Data via Causal Optimal Transportcited by 70
  8. 2018Generative Adversarial User Model for Reinforcement Learning Based Recommendation Systemcited by 64
  9. 2020Few-Shot Adaptation of Generative Adversarial Networkscited by 64
  10. 2016Generative Multi-Adversarial Networkscited by 60
  11. 2017Multi-Agent Diverse Generative Adversarial Networkscited by 59
  12. 2018MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasetscited by 49
  13. 2020Generating Realistic Stock Market Order Streamscited by 30
  14. 2020Decision-Aware Conditional GANs for Time Series Datacited by 11
  15. 2020Brainstorming Generative Adversarial Networks (BGANs): Towards Multi-Agent Generative Models with Distributed Private Datasetscited by 7

Built on by

Not cited yet.