Reinforcement Learning With LLMs Interaction For Distributed Diffusion Model Services
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909589074608128 |
|---|---|
| author | Du, Hongyang Zhang, Ruichen Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Shen, Xuemin Kim, Dong In |
| author_facet | Du, Hongyang Zhang, Ruichen Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Shen, Xuemin Kim, Dong In |
| contents | Distributed Artificial Intelligence-Generated Content (AIGC) has attracted significant attention, but two key challenges remain: maximizing subjective Quality of Experience (QoE) and improving energy efficiency, which are particularly pronounced in widely adopted Generative Diffusion Model (GDM)-based image generation services. In this paper, we propose a novel user-centric Interactive AI (IAI) approach for service management, with a distributed GDM-based AIGC framework that emphasizes efficient and cooperative deployment. The proposed method restructures the GDM inference process by allowing users with semantically similar prompts to share parts of the denoising chain. Furthermore, to maximize the users' subjective QoE, we propose an IAI approach, i.e., Reinforcement Learning With Large Language Models Interaction (RLLI), which utilizes Large Language Model (LLM)-empowered generative agents to replicate user interaction, providing real-time and subjective QoE feedback aligned with diverse user personalities. Lastly, we present the GDM-based Deep Deterministic Policy Gradient (GDDPG) algorithm, adapted to the proposed RLLI framework, to allocate communication and computing resources effectively while accounting for subjective user traits and dynamic wireless conditions. Simulation results demonstrate that G-DDPG improves total QoE by 15% compared with the standard DDPG algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_11094 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Reinforcement Learning With LLMs Interaction For Distributed Diffusion Model Services Du, Hongyang Zhang, Ruichen Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Shen, Xuemin Kim, Dong In Networking and Internet Architecture Distributed Artificial Intelligence-Generated Content (AIGC) has attracted significant attention, but two key challenges remain: maximizing subjective Quality of Experience (QoE) and improving energy efficiency, which are particularly pronounced in widely adopted Generative Diffusion Model (GDM)-based image generation services. In this paper, we propose a novel user-centric Interactive AI (IAI) approach for service management, with a distributed GDM-based AIGC framework that emphasizes efficient and cooperative deployment. The proposed method restructures the GDM inference process by allowing users with semantically similar prompts to share parts of the denoising chain. Furthermore, to maximize the users' subjective QoE, we propose an IAI approach, i.e., Reinforcement Learning With Large Language Models Interaction (RLLI), which utilizes Large Language Model (LLM)-empowered generative agents to replicate user interaction, providing real-time and subjective QoE feedback aligned with diverse user personalities. Lastly, we present the GDM-based Deep Deterministic Policy Gradient (GDDPG) algorithm, adapted to the proposed RLLI framework, to allocate communication and computing resources effectively while accounting for subjective user traits and dynamic wireless conditions. Simulation results demonstrate that G-DDPG improves total QoE by 15% compared with the standard DDPG algorithm. |
| title | Reinforcement Learning With LLMs Interaction For Distributed Diffusion Model Services |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2311.11094 |