Innovation in the Age of Regulation: Federated Learning with Flower
summary
Demonstrates that training without centralizing sensitive records is practical: a demo uses Flower to run a server on port 880, spin up clients running simple MLPs, exchange model weights and perform federated averaging, and shows reduced storage and training costs versus central training. Highlights three useful features — model weight compression, custom metrics and aggregation — and three constraints: client compute limits, network reliability, and harder preprocessing. Reports successful cross‑hospital experiments for healthcare models and FDA documentation workarounds.
AI-written summary · about
chapters (10)
- 0:00Federated learning basics
- 3:19Classical ML limits under regulation
- 6:53Privacy and scalability solutions
- 9:21Flower features and tools
- 13:56Flower architecture and workflow
- 16:29Flower server and client setup
- 19:38Real-world FL advantages
- 20:22FL implementation challenges
- 22:55Summary and future of FL
- 23:16Q&A on pricing, weights, security
related talks
57mKeynote: Federated Learning with Flower: AI's Next Frontier
32mPlant a Touch-Me-Not: Train Models Without Anyone Touching Your Data with Flower
18mEnabling Medical AI through Federated Learning
26mMachine Learning without the Data #federatedlearning
01h 22mThe future of AI training is federated
42mLearning Together, Distributed: An Introduction to Federated Learning
28mA Privacy Enhancing Federated Learning Framework for Multi-Party Distributed ..
13mScalable and Portable Federated Learning Simulation Engine