让大模型在边缘设备上高效运行，兼顾隐私与速度。
Federated Intelligence: When Large AI Models Meet Federated Fine-Tuning and Collaborative Reasoning at the Network Edge
- 采用联邦微调适应边缘任务，分簇分层异步降低通信开销。
- 仿真显示多种下游任务下微调损失显著下降。
- 适合关注边缘智能、隐私保护的开发者和研究者。
大型人工智能模型在诸多应用场景中表现出卓越能力，但在网络边缘部署面临数据隐私、计算资源和延迟等挑战。本文探讨联邦微调与协同推理技术，推动大模型在资源受限无线网络中的应用。首先分析大模型在特定领域的潜在应用；随后提出联邦微调方法，使大模型在边缘端适配具体任务或环境，有效缓解通信开销问题，提升通信效率。所提方法遵循分簇、分层、异步范式，有助于解决隐私问题并打破数据孤岛。此外，为提升运行效率并降低延迟，构建了高效的模型协同推理框架，涵盖去中心化横向协作、云-边-端纵向协作及多接入协作。仿真结果表明，所提方法在多种下游任务中显著降低大模型微调损失。最后，本文还指出了若干开放挑战与研究机遇。
原文摘要 · Abstract (English)
Large artificial intelligence (AI) models exhibit remarkable capabilities in various application scenarios, but deploying them at the network edge poses significant challenges due to issues such as data privacy, computational resources, and latency. In this paper, we explore federated fine-tuning and collaborative reasoning techniques to facilitate the implementation of large AI models in resource-constrained wireless networks. Firstly, promising applications of large AI models within specific domains are discussed. Subsequently, federated fine-tuning methods are proposed to adapt large AI models to specific tasks or environments at the network edge, effectively addressing the challenges associated with communication overhead and enhancing communication efficiency. These methodologies follow clustered, hierarchical, and asynchronous paradigms to effectively tackle privacy issues and eliminate data silos. Furthermore, to enhance operational efficiency and reduce latency, efficient frameworks for model collaborative reasoning are developed, which include decentralized horizontal collaboration, cloud-edge-end vertical collaboration, and multi-access collaboration. Next, simulation results demonstrate the effectiveness of our proposed methods in reducing the fine-tuning loss of large AI models across various downstream tasks. Finally, several open challenges and research opportunities are outlined.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。