Exploring Collaborative Distributed Diffusion-Based AI-Generated Content (AIGC) in Wireless Networks

Abstract

Distributed Artificial Intelligence-Generated Content (AIGC) has attracted increasing attention. However, it faces two significant challenges: how to maximize the subjective Quality of Experience (QoE) and how to enhance the energy efficiency, which are particularly pronounced in widely adopted Generative Diffusion Model (GDM)-based AIGC services for image generation. In this paper, we propose a novel user-centric Interactive AI (IAI) approach for service management, with a distributed GDM-based AIGC framework, prioritizing efficient and collaborative GDM deployment. Specifically, we restructure the GDM's inference process, i.e., the denoising chain, to enable users' semantically similar prompts to share a portion of diffusion steps. Furthermore, to maximize the users' subjective QoE, we propose a IAI approach, i.e., Reinforcement Learning With Large Language Models Interaction (RLLI), which utilizes Large Language Model (LLM)-empowered generative agents to replicate users interaction, providing real-time and subjective QoE feedback that reflects a spectrum of user personalities. Lastly, we present the GDM-based Deep Deterministic Policy Gradient (G-DDPG) algorithm, adapted to the proposed RLLI framework, for effective communication and computing resource allocation while considering user subjective personalities and dynamic wireless environments in decision-making. Simulation results show that G-DDPG can increase the sum QoE by 15%, compared with the conventional DDPG algorithm.

Reinforcement Learning With Large Language Models (LLMs) Interaction For Network Services

“…T HE demand for artificial intelligence-generated content (AIGC) services in areas including multimedia and business [1] is propelled by advanced generative AI (GAI) models, which offer scalable and consistent output in text and imagery [2]. For instance, ChatGPT attracted more than 100 million active users within two months [3], highlighting its impact on text-based interactions [3].…”

A Study Of Civil Engineering Education At Singapore Nanyang Technology University And At The University Of Florida

“…The AIGC framework offers a significant advantage in terms of personalization, a feature that sets it apart from traditional SemCom. While traditional SemCom often remains constrained to transmitting generic semantic information, the SemCom-enabled AIGC framework exhibits the ability to tailor the generation of content to specific scenarios or user preferences such as personal driving assistant and smart healthcare [2].…”

“…The diverse nature of AIGC services poses an intriguing challenge in developing universal evaluation metrics [2]. Current metrics exhibit varying responses based on the specific requirements of different AIGC services.…”

“…The efficient functioning and widespread adoption of AIGC services are contingent on robust communication infrastructure and technologies, such as wireless networks and semantic communication (SemCom). The technologies offer many benefits to AIGC services including [2]:…”