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

TL;DR

Meta-SimGNN tackles practical WiFi indoor localization by addressing both environmental scenario shifts and dynamic device configurations that alter CSI dimensionality. It combines a graph neural network with a fine-grained CSI graph constructed via amplitude-phase fusion and spatial pyramid pooling, enabling dimension-consistent node features and robust localization across varying AP counts and bandwidths. A similarity-guided meta-learning strategy selects scenario-specific initial parameters to rapidly adapt to new environments, improving generalization and reducing fine-tuning data needs. Experimental results on commodity WiFi hardware across multiple scenarios show that Meta-SimGNN achieves superior localization accuracy and rapid adaptability compared to state-of-the-art baselines, highlighting its potential for robust, scalable deployment in real-world deployments.

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.

Figures (18)

• Figure 1: The structure of GNN.
• Figure 2: The framework of Meta-SimGNN.
• Figure 3: CSI amplitude before and after filtering.
• Figure 5: The CSI image for different channels at location 1.
• Figure 7: Feature extraction based on spatial pyramid pooling.