Decentralized Federated Learning for UAV Networks: Architecture, Challenges, and Opportunities

摘要

Unmanned aerial vehicles (UAVs), or drones, are envisioned to support extensive applications in next-generation wireless networks in both civil and military fields. Empowering UAV networks' intelligence with artificial intelligence, especially machine learning (ML), techniques, is inevitable and appealing to enable the aforementioned applications. To solve the problems of traditional cloud-centric ML for UAV networks such as privacy concerns, unacceptable latency, and resource burden, a distributed ML technique, federated learning (FL), recently has been proposed to enable multiple UAVs to collaboratively train an ML model without letting out raw data. However, almost all existing FL paradigms are still centralized (i.e., a central entity is in charge of ML model aggregation and fusion over the whole network), which could result in the issue of a single point of failure and are inappropriate to UAV networks with both unreliable nodes and links. Thus motivated, in this article, we propose a novel architecture called Decentralized Federated Learning for UAV Networks (DFL-UN), which enables FL within UAV networks without a central entity. We also conduct a preliminary simulation study to validate the feasibility and effectiveness of the DFLUN architecture. Finally, we discuss the main challenges and potential research directions in the DFL-UN.