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

arXiv: https://arxiv.org/abs/2201.09644 · HTML: https://mlsanity.com/paper/2201.09644/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 24 Jan 2022.

## Builds on (most cited first, 27 of 27)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Coupled Generative Adversarial Networks](https://mlsanity.com/paper/1606.07536/) (2016)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Transferring GANs: generating images from limited data](https://mlsanity.com/paper/1805.01677/) (2018)
- [Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs](https://mlsanity.com/paper/2002.10964/) (2020)
- [Few-shot Image Generation with Elastic Weight Consolidation](https://mlsanity.com/paper/2012.02780/) (2020)
- [MineGAN: effective knowledge transfer from GANs to target domains with few images](https://mlsanity.com/paper/1912.05270/) (2019)
- [Image Generation From Small Datasets via Batch Statistics Adaptation](https://mlsanity.com/paper/1904.01774/) (2019)
- [FedGAN: Federated Generative Adversarial Networks for Distributed Data](https://mlsanity.com/paper/2006.07228/) (2020)
- [Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning](https://mlsanity.com/paper/1805.10000/) (2018)
- [COT-GAN: Generating Sequential Data via Causal Optimal Transport](https://mlsanity.com/paper/2006.08571/) (2020)
- [Generative Adversarial User Model for Reinforcement Learning Based Recommendation System](https://mlsanity.com/paper/1812.10613/) (2018)
- [Few-Shot Adaptation of Generative Adversarial Networks](https://mlsanity.com/paper/2010.11943/) (2020)
- [Generative Multi-Adversarial Networks](https://mlsanity.com/paper/1611.01673/) (2016)
- [Multi-Agent Diverse Generative Adversarial Networks](https://mlsanity.com/paper/1704.02906/) (2017)
- [MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets](https://mlsanity.com/paper/1811.03850/) (2018)
- [Generating Realistic Stock Market Order Streams](https://mlsanity.com/paper/2006.04212/) (2020)
- [Decision-Aware Conditional GANs for Time Series Data](https://mlsanity.com/paper/2009.12682/) (2020)
- [Brainstorming Generative Adversarial Networks (BGANs): Towards Multi-Agent Generative Models with Distributed Private Datasets](https://mlsanity.com/paper/2002.00306/) (2020)

## 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.