Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models
Chen, Changyu, Bose, Avinandan, Cheng, Shih-Fen, Sinha, Arunesh
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.
Jan-24-2022
- Genre:
- Research Report > New Finding (0.67)
- Industry:
- Energy > Power Industry (0.68)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (1.00)
- Natural Language > Generation (1.00)
- Representation & Reasoning > Agents (1.00)
- Information Technology > Artificial Intelligence