Placeholder chapter page. Sections are produced by the book-skills pipeline.
Sections
- 64.1 Why raw sensor data may not leave the device
- 64.2 Federated learning (FedAvg family) and non-IID sensors
- 64.3 Personalization and local adaptation
- 64.4 Differential privacy and secure aggregation
- 64.5 Split and split-federated learning
- 64.6 Multimodal and cross-device federation
- 64.7 Federated evaluation, security, and failure modes
Lab 64
simulate federated training across users/devices for a wearable model; add differential privacy and measure the utility cost.