FGATT: A Robust Framework for Wireless Data Imputation Using Fuzzy Graph Attention Networks and Transformer Encoders

TL;DR

FGATT tackles missing data in wireless sensor networks by integrating fuzzy graph attention with a Transformer encoder to capture spatial and temporal dependencies for imputation. It introduces a self-adaptive dynamic graph construction based on fuzzy rough sets, paired with FGAT layers for robust spatial representation and a Transformer encoder for temporal modeling. Empirical results on SWaT datasets show FGATT achieving superior imputation accuracy and robustness across high missingness, outperforming FFN, BGRU, Transformer, and TGCN baselines. The approach holds practical impact for IoT and wireless networks, enabling more reliable sensing and analytics in data-impaired environments.

Abstract

Missing data is a pervasive challenge in wireless networks and many other domains, often compromising the performance of machine learning and deep learning models. To address this, we propose a novel framework, FGATT, that combines the Fuzzy Graph Attention Network (FGAT) with the Transformer encoder to perform robust and accurate data imputation. FGAT leverages fuzzy rough sets and graph attention mechanisms to capture spatial dependencies dynamically, even in scenarios where predefined spatial information is unavailable. The Transformer encoder is employed to model temporal dependencies, utilizing its self-attention mechanism to focus on significant time-series patterns. A self-adaptive graph construction method is introduced to enable dynamic connectivity learning, ensuring the framework's applicability to a wide range of wireless datasets. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in imputation accuracy and robustness, particularly in scenarios with substantial missing data. The proposed model is well-suited for applications in wireless sensor networks and IoT environments, where data integrity is critical.

Figures (3)

• Figure 1: Fuzzy Graph Attention-Transformer Network
• Figure 2: Performance Evaluation on SWaT.A7.22
• Figure 3: Performance Evaluation on SWaT.A7.29