Federated Learning for Edge Intelligence

The field of edge intelligence is witnessing a significant shift towards federated learning, enabling privacy-aware and scalable AI solutions. Recent developments focus on integrating federated learning with edge devices, such as head-worn sensors and maritime vessels, to enhance situational awareness and anomaly detection. Noteworthy papers include:

  • Multi-Frequency Federated Learning for Human Activity Recognition, which proposes a novel approach for joint ML model learning across devices with varying sampling frequencies.
  • Over-the-Air Federated Learning, which presents a comprehensive guide to AirFL, a paradigm that integrates wireless signal processing and distributed machine learning.
  • Federated Learning for Anomaly Detection in Maritime Movement Data, which introduces M3fed, a novel solution for federated learning of movement anomaly detection models.

Sources

Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors

Joint Sensing, Communication, and Computation for Vertical Federated Edge Learning in Edge Perception Network

Federated Learning and Trajectory Compression for Enhanced AIS Coverage

Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing

Federated Learning for Anomaly Detection in Maritime Movement Data

Built with on top of