Toward Scalable Generative AI via Mixture of Experts in Mobile Edge Networks

Abstract

The advancement of generative artificial intelligence (GAI) has driven revolutionary applications like ChatGPT. The widespread use of these applications relies on a mixture of experts (MoE), which contains multiple experts, and selectively engages them for each task to lower operation costs while maintaining performance. Despite MoE, GAI faces challenges in resource consumption when deployed on user devices. Hence, this article proposes mobile edge networks supported MoE-based GAI. We first review the MoE from traditional AI and GAI perspectives, including structure, principles, and applications. We then propose a framework that transfers subtasks to experts in mobile edge networks, aiding GAI model operation on user devices. We discuss challenges in this process and introduce a deep reinforcement learning-based algorithm to select edge experts for subtask execution. Experimental results show that our framework not only facilitates GAI's deployment on resource-limited devices, but also generates higher-quality content compared to methods without edge network support.