Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

RadioDiff-FS: Physics-Informed Manifold Alignment in Few-Shot Diffusion Models for High-Fidelity Radio Map Construction

Xiucheng Wang, Zixuan Guo, Nan Cheng

Abstract

Radio maps (RMs) provide spatially continuous propagation characterizations essential for 6G network planning, but high-fidelity RM construction remains challenging. Rigorous electromagnetic solvers incur prohibitive computational latency, while data-driven models demand massive labeled datasets and generalize poorly from simplified simulations to complex multipath environments. This paper proposes RadioDiff-FS, a few-shot diffusion framework that adapts a pre-trained main-path generator to multipath-rich target domains with only a small number of high-fidelity samples. The adaptation is grounded in a theoretical decomposition of the multipath RM into a dominant main-path component and a directionally sparse residual. This decomposition shows that the cross-domain shift corresponds to a bounded and geometrically structured feature translation rather than an arbitrary distribution change. A Direction-Consistency Loss (DCL) is then introduced to constrain diffusion score updates along physically plausible propagation directions, suppressing phase-inconsistent artifacts that arise in the low-data regime. Experiments show that RadioDiff-FS reduces NMSE by 59.5% on static RMs and by 74.0% on dynamic RMs relative to the vanilla diffusion baseline, achieving an SSIM of 0.9752 and a PSNR of 36.37 dB under severely limited supervision.

RadioDiff-FS: Physics-Informed Manifold Alignment in Few-Shot Diffusion Models for High-Fidelity Radio Map Construction

Abstract

Radio maps (RMs) provide spatially continuous propagation characterizations essential for 6G network planning, but high-fidelity RM construction remains challenging. Rigorous electromagnetic solvers incur prohibitive computational latency, while data-driven models demand massive labeled datasets and generalize poorly from simplified simulations to complex multipath environments. This paper proposes RadioDiff-FS, a few-shot diffusion framework that adapts a pre-trained main-path generator to multipath-rich target domains with only a small number of high-fidelity samples. The adaptation is grounded in a theoretical decomposition of the multipath RM into a dominant main-path component and a directionally sparse residual. This decomposition shows that the cross-domain shift corresponds to a bounded and geometrically structured feature translation rather than an arbitrary distribution change. A Direction-Consistency Loss (DCL) is then introduced to constrain diffusion score updates along physically plausible propagation directions, suppressing phase-inconsistent artifacts that arise in the low-data regime. Experiments show that RadioDiff-FS reduces NMSE by 59.5% on static RMs and by 74.0% on dynamic RMs relative to the vanilla diffusion baseline, achieving an SSIM of 0.9752 and a PSNR of 36.37 dB under severely limited supervision.
Paper Structure (18 sections, 65 equations, 4 figures, 4 tables)

This paper contains 18 sections, 65 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work and Preliminary
  3. RM Construction Methods
  4. EM Computing Methods for RM Construction
  5. Denoising Diffusion Model
  6. System Model and Problem Formulation
  7. Few-Shot DM for RM Construction
  8. Main-Path Decomposition
  9. Feature Shift Geometry
  10. Directional Consistency Principle
  11. Few-Shot Fine-Tuning
  12. Experiments Results
  13. Datasets
  14. Metrics and Baseline
  15. Performance on SRM
  16. ...and 3 more sections

Figures (4)

  • Figure 1: Illustration of the few-shot in RM.
  • Figure 2: The RadioDiff-FS framework. The model pre-trains on abundant main-path data (left) and adapts to the multipath target domain using few-shot supervision (middle), whose transfer is enabled by physics-informed manifold alignment.
  • Figure 3: The comparisons of constructed SRM on different methods.
  • Figure 4: The comparisons of constructed DRM on different methods.