29 January 2024 in IEEE Sensors Journal
The Federated distillation (FD) paradigm has been recently proposed as a promising alternative to federated learning (FL), especially in wireless sensor networks with limited communication resources. However, all state-of-the-art FD algorithms are designed for classification tasks only, and less attention has been given to regression tasks. To take advantage of this promising paradigm for localization which is inherently a regression problem, we introduce in this work an FD framework that is tailored to address regression learning problems. More specifically, we propose an FD-based indoor localization system that shows a good trade-off communication load vs. accuracy compared to FL-based indoor localization. With our proposed framework, we reduce the number of transmitted bits by up to 98%. We analyze the energy efficiency regarding the number of communication rounds for both FD and FL systems to achieve the same localization accuracy. The results revealed that FD comes with greater energy efficiency by reasonably saving transmission energy at the expense of computation energy. This notably represents a significant advantage in the context of wireless sensor networks, particularly given the prevalence of battery-powered IoT devices operating with constrained bandwidth. Moreover, we show that the proposed framework is much more scalable than FL and, thus more likely to cope with the expansion of wireless networks.
7 August 2024 in IEEE Internet of Things Journal
The proliferation of the Internet of Things fosters collaboration among connected devices for tasks like indoor localization. However, existing indoor localization solutions struggle with dynamic and harsh conditions, requiring extensive data collection and environment-specific calibration. These factors impede cooperation, scalability, and the utilization of prior research efforts. To address these challenges, we propose FeMLoc, a federated meta-learning framework for localization. FeMLoc operates in two stages: (i) collaborative meta-training, where edge devices contribute diverse localization data to train a global meta-model using a combination of model-agnostic meta-learning and federated averaging techniques. (ii) Rapid adaptation for new environments, where the pre-trained global meta-model initializes localization models, requiring only minimal fine-tuning with a small amount of new data. In this paper, we provide a detailed technical overview of FeMLoc, highlighting its unique approach to privacy-preserving meta-learning in the context of indoor localization. Our performance evaluations on real-world datasets including UJIIndoorLoc demonstrate the superiority of FeMLoc over state-of-the-art methods, enabling swift adaptation to new indoor environments with reduced calibration effort. Specifically, FeMLoc achieves up to 80.95% improvement in localization accuracy compared to the conventional baseline neural network (NN) approach after only 100 gradient steps. Alternatively, for a target accuracy of around 5m, FeMLoc achieves the same level of accuracy up to 82.21% faster than the baseline NN approach. This translates to FeMLoc requiring fewer training iterations, thereby significantly reducing fingerprint data collection and calibration efforts. Moreover, FeMLoc exhibits enhanced scalability, making it well-suited for location-aware massive connectivity driven by emerging wireless communication technologies.
16 September 2025 in arXiv
WCWilfrid Sougrinoma Compaoré
Wilfrid Sougrinoma Compaoré
Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative machine learning while preserving data privacy, making it particularly suitable for Internet of Things (IoT) environments. However, resource-constrained IoT devices face significant challenges due to limited energy,unreliable communication channels, and the impracticality of assuming infinite blocklength transmission. This paper proposes a federated learning framework for IoT networks that integrates finite blocklength transmission, model quantization, and an error-aware aggregation mechanism to enhance energy efficiency and communication reliability. The framework also optimizes uplink transmission power to balance energy savings and model performance. Simulation results demonstrate that the proposed approach significantly reduces energy consumption by up to 75\% compared to a standard FL model, while maintaining robust model accuracy, making it a viable solution for FL in real-world IoT scenarios with constrained resources. This work paves the way for efficient and reliable FL implementations in practical IoT deployments. Index Terms: Federated learning, IoT, finite blocklength, quantization, energy efficiency.