Search papers, labs, and topics across Lattice.
This paper introduces FedRings, a decentralized federated learning framework specifically designed for low Earth orbit (LEO) satellite constellations, addressing the challenges posed by dynamic topologies and intermittent connectivity. By implementing a ring-based communication structure and a spatio-temporal routing strategy, FedRings optimizes model exchange to align with visibility windows, while adaptive sparse incremental aggregation minimizes communication overhead. Experimental results demonstrate that FedRings significantly outperforms traditional methods in terms of efficiency and stability in realistic LEO scenarios.
FedRings cuts communication costs and enhances learning stability in dynamic LEO satellite networks, outperforming existing federated learning approaches.
Federated learning over low Earth orbit (LEO) satellite networks is limited by frequent link changes, short contact times, and a highly dynamic topology, making centralized or synchronized training inefficient and hard to scale. To address this, we propose FedRings, a decentralized framework that organizes satellites into ring-based communication structures. It uses a spatio-temporal routing strategy with link-aware communication scheduling to align model exchange with actual visibility windows and time-varying connectivity patterns in LEO. Model updates are propagated along the ring using adaptive sparse incremental aggregation, which reduces communication overhead by progressively combining and compressing updates. To handle communication interruptions, a historical compensation mechanism maintains training continuity. By combining topology-aware routing, communication scheduling, and efficient aggregation, FedRings enables stable and efficient learning in dynamic LEO networks while reducing communication cost, and experiments show it consistently outperforms existing methods in realistic settings.
