Meta-SimGNN: Adaptive and Robust WiFi Localization Across Dynamic Configurations and Diverse Scenarios

2025-11-17

AI Summary

Deep learning-based WiFi localization suffers from poor generalization when device configurations—such as AP count, bandwidth, and antenna number—vary across deployments, causing inconsistent CSI dimensionality and hindering model transferability. Method: This paper proposes a graph neural network (GNN)–meta-learning hybrid framework. It constructs a fine-grained CSI graph to explicitly model inter-AP relationships, introduces an amplitude-phase fused CSI image representation with a consistency-aware feature extraction mechanism, and employs a meta-initialization strategy guided by historical scene similarity to robustly adapt to input dimensional variations and enable rapid cross-scenario adaptation. Contribution/Results: Evaluated on multiple real-world scenarios, the method significantly improves both localization accuracy and generalization under configuration and environmental changes. It is the first work to systematically address the transferability challenge of deep WiFi localization models under dynamic device configurations.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

To promote the practicality of deep learning-based localization, existing studies aim to address the issue of scenario dependence through meta-learning. However, these studies primarily focus on variations in environmental layouts while overlooking the impact of changes in device configurations, such as bandwidth, the number of access points (APs), and the number of antennas used. Unlike environmental changes, variations in device configurations affect the dimensionality of channel state information (CSI), thereby compromising neural network usability. To address this issue, we propose Meta-SimGNN, a novel WiFi localization system that integrates graph neural networks with meta-learning to improve localization generalization and robustness. First, we introduce a fine-grained CSI graph construction scheme, where each AP is treated as a graph node, allowing for adaptability to changes in the number of APs. To structure the features of each node, we propose an amplitude-phase fusion method and a feature extraction method. The former utilizes both amplitude and phase to construct CSI images, enhancing data reliability, while the latter extracts dimension-consistent features to address variations in bandwidth and the number of antennas. Second, a similarity-guided meta-learning strategy is developed to enhance adaptability in diverse scenarios. The initial model parameters for the fine-tuning stage are determined by comparing the similarity between the new scenario and historical scenarios, facilitating rapid adaptation of the model to the new localization scenario. Extensive experimental results over commodity WiFi devices in different scenarios show that Meta-SimGNN outperforms the baseline methods in terms of localization generalization and accuracy.

Problem

• Addresses WiFi localization dependence on specific device configurations like bandwidth and AP count
• Solves dimensionality inconsistency in CSI data caused by varying antenna configurations
• Enhances localization robustness across diverse scenarios and dynamic environmental changes

Innovation

• Graph neural networks adapt to varying access points
• Amplitude-phase fusion enhances channel state information reliability
• Similarity-guided meta-learning enables rapid scenario adaptation