SpaceMoE partitions MoE layers across orbiting satellite subnets in a ring and optimizes expert placement by activation probability and path latency, yielding at least 3x lower inference latency in thousand-satellite simulations versus random baselines.
Optimal batch-size control for low-latency federated learning with device heterogeneity,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SpaceMoE: Realizing Distributed Mixture-of-Experts Inference over Space Networks
SpaceMoE partitions MoE layers across orbiting satellite subnets in a ring and optimizes expert placement by activation probability and path latency, yielding at least 3x lower inference latency in thousand-satellite simulations versus random baselines.