loading page

Leveraging Transfer Learning for Radio Map Estimation via Mixture of Experts
  • +1
  • Rahul Kumar Jaiswal ,
  • Mohamed Elnourani ,
  • Siddharth Deshmukh ,
  • Baltasar Beferull-Lozano
Rahul Kumar Jaiswal
University of Agder

Corresponding Author:[email protected]

Author Profile
Mohamed Elnourani
Author Profile
Siddharth Deshmukh
Author Profile
Baltasar Beferull-Lozano
Author Profile

Abstract

This paper leverages transfer learning~(TL) on a mixture of experts~(MoE) model for radio map estimation. The proposed MoE combines location-based and location-free experts through a gating network exploiting their complementary benefits. To estimate the radio map in a new wireless environment, the learned model of another sufficiently similar environment is transferred and fine-tuned with additional data from the new environment. The proposed data-driven similarity measure predicts the amount of data needed for TL. Results demonstrate that the proposed method only requires 20-40\% of measurements to adapt to several varying environments, and as expected, the proposed MoE method outperforms both experts.