Fed-Meta-Align: A Similarity-Aware Aggregation and Personalization Pipeline for Federated TinyML on Heterogeneous Data

2025-08-15

AI Summary

Real-time fault classification for resource-constrained IoT devices suffers from model divergence in federated learning (FL) under non-IID data. To address this, we propose a four-stage FL framework: (1) sequence-aware meta-initialization to improve initialization consistency across heterogeneous devices; (2) cosine-similarity-based dual-criterion aggregation to enhance global model robustness; (3) device-level personalized fine-tuning to adapt to local data distributions; and (4) lightweight TinyML deployment to ensure real-time inference. The method integrates meta-learning, similarity-aware weighting, and local adaptation—without requiring centralized data. Evaluated on electrical and mechanical fault datasets, our approach achieves a mean accuracy of 91.27%, outperforming FedAvg (+3.87%) and FedProx (+3.37%). It establishes an efficient, scalable, and edge-deployable distributed learning paradigm for industrial intelligent monitoring.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Intelligent Robots: State Estimation
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Real-time fault classification in resource-constrained Internet of Things (IoT) devices is critical for industrial safety, yet training robust models in such heterogeneous environments remains a significant challenge. Standard Federated Learning (FL) often fails in the presence of non-IID data, leading to model divergence. This paper introduces Fed-Meta-Align, a novel four-phase framework designed to overcome these limitations through a sophisticated initialization and training pipeline. Our process begins by training a foundational model on a general public dataset to establish a competent starting point. This model then undergoes a serial meta-initialization phase, where it sequentially trains on a subset of IOT Device data to learn a heterogeneity-aware initialization that is already situated in a favorable region of the loss landscape. This informed model is subsequently refined in a parallel FL phase, which utilizes a dual-criterion aggregation mechanism that weights for IOT devices updates based on both local performance and cosine similarity alignment. Finally, an on-device personalization phase adapts the converged global model into a specialized expert for each IOT Device. Comprehensive experiments demonstrate that Fed-Meta-Align achieves an average test accuracy of 91.27% across heterogeneous IOT devices, outperforming personalized FedAvg and FedProx by up to 3.87% and 3.37% on electrical and mechanical fault datasets, respectively. This multi-stage approach of sequenced initialization and adaptive aggregation provides a robust pathway for deploying high-performance intelligence on diverse TinyML networks.

Problem

• Addresses non-IID data challenges in federated learning for IoT
• Improves fault classification accuracy on heterogeneous tiny devices
• Enables robust model training across diverse IoT networks

Innovation

• Meta-initialization phase for heterogeneity-aware model starting point
• Dual-criterion aggregation weighting updates by performance and similarity
• On-device personalization phase creating specialized expert models