Environment-Conditioned Diffusion Meta-Learning for Data-Efficient WiFi Localization

TL;DR

EnvCoLoc is a novel environment-conditioned diffusion meta-learning framework that significantly improves WiFi localization accuracy in new environments with limited data by leveraging geometry-aware priors.

Contribution

It introduces a diffusion-based meta-learning approach that incorporates environmental geometry into the localization process, enhancing cross-environment generalization.

Findings

Achieves up to 20.0% reduction in mean localization error in NLOS scenarios.

Effectively captures environment-dependent variations with limited support samples.

Outperforms baseline methods in real-world experiments.

Abstract

Fingerprinting-based localization often suffers from poor cross-environment generalization, especially when only a few labeled samples are available in the target environment. Existing methods mitigate distribution shifts through domain adaptation or improved signal representations, but they usually ignore environmental geometry or use it in a deterministic manner, limiting their ability to capture diverse multipath variations in complex propagation conditions. To address this issue, we propose EnvCoLoc, an environment-conditioned diffusion meta-learning framework for few-shot fingerprinting localization. EnvCoLoc extracts structured descriptors from 3D point clouds and uses them to condition a latent diffusion generator, which produces environment-specific parameter offsets to modulate a shared meta-learned initialization. This design injects geometry-aware priors into the adaptation process and provides more informative initializations for new environments. To learn the stochastic mapping from coarse environmental descriptors to high-dimensional parameter corrections under limited data, the diffusion generator and localization network are jointly optimized within a two-loop meta-learning framework. The generated offsets capture systematic environment-dependent variations, while gradient-based inner-loop adaptation further refines the model to reduce residual task-specific mismatch. We also provide an excess-loss analysis for finite-step adaptation, theoretically supporting the benefit of geometry-aware initialization. Real-world experiments show that EnvCoLoc consistently improves localization accuracy over baseline methods, achieving up to a 20.0% reduction in mean localization error in NLOS scenarios with only 10 support samples.