Federated learning is a distributed machine learning paradigm in which multiple clients (e.g., IoT devices, smart building nodes, or WiFi sensing systems) collaboratively train a shared global model by exchanging only model parameters or gradients rather than raw local data, thereby preserving data privacy. In the context of WiFi/CSI sensing and smart building occupancy prediction, it matters because it enables models to benefit from diverse, heterogeneous sensing environments and user behaviors without centralizing sensitive data, addressing a key barrier to real-world deployment. Key variants relevant to the field include horizontal federated learning (clients share the same feature space but different data samples), vertical federated learning (clients share samples but different feature spaces), and federated transfer learning (which combines federated training with domain adaptation to handle cross-domain shifts, such as those addressed in cross-domain gesture recognition systems like WiGNN).
Source Papers
- Occupancy Prediction in IoT-Enabled Smart Buildings: Technologies, Methods, and Future Directions ↗ — Occupancy Prediction in IoT-Enabled Smart Buildings: Technol
- WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired by Dynamic Topology Structure ↗ — WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired