Multiscale generative models: Improving performance of a generative model using feedback from other dependent generative models
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 a...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6792 https://ink.library.smu.edu.sg/context/sis_research/article/7795/viewcontent/MGM_AAAI22.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-7795 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-77952022-01-27T09:58:11Z 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 higherlevel 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. 2022-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6792 https://ink.library.smu.edu.sg/context/sis_research/article/7795/viewcontent/MGM_AAAI22.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Artificial Intelligence and Robotics |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Artificial Intelligence and Robotics |
spellingShingle |
Artificial Intelligence and Robotics CHEN, Changyu BOSE, Avinandan CHENG, Shih-Fen SINHA, Arunesh Multiscale generative models: Improving performance of a generative model using feedback from other dependent generative models |
description |
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 higherlevel 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. |
format |
text |
author |
CHEN, Changyu BOSE, Avinandan CHENG, Shih-Fen SINHA, Arunesh |
author_facet |
CHEN, Changyu BOSE, Avinandan CHENG, Shih-Fen SINHA, Arunesh |
author_sort |
CHEN, Changyu |
title |
Multiscale generative models: Improving performance of a generative model using feedback from other dependent generative models |
title_short |
Multiscale generative models: Improving performance of a generative model using feedback from other dependent generative models |
title_full |
Multiscale generative models: Improving performance of a generative model using feedback from other dependent generative models |
title_fullStr |
Multiscale generative models: Improving performance of a generative model using feedback from other dependent generative models |
title_full_unstemmed |
Multiscale generative models: Improving performance of a generative model using feedback from other dependent generative models |
title_sort |
multiscale generative models: improving performance of a generative model using feedback from other dependent generative models |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2022 |
url |
https://ink.library.smu.edu.sg/sis_research/6792 https://ink.library.smu.edu.sg/context/sis_research/article/7795/viewcontent/MGM_AAAI22.pdf |
_version_ |
1770576069811765248 |