AirMoE: Realizing Over-the-Air Distributed Mixture-of-Experts Inference at the Wireless Edge
An inference-aware AirMoE error metric is constructed to quantify aggregation distortion effects on end-to-end (E2E) inference accuracy via perturbation-based layer-sensitivity calibration, and an activation- and channel-aware expert placement strategy is developed that assigns more important experts to devices with lower channel-power cost.
Huiling Yang, Zhanwei Wang, Kaibin Huang
· 0 citations