Federated Learning: So Close and Yet So Out of Reach
summary
Federated learning is presented as an algorithmic approach to training models on private data, with technical details demonstrated using NVIDIA FLARE. The talk covers motivations, implementation mechanics, results and pitfalls, plus how recent EU AI Act legislation will affect federated learning, and includes a concrete example and research directions.
AI-written summary · about
chapters (13)
- 0:00Intro
- 1:27What is Federated Learning?
- 3:23Why Choose It?
- 5:39What Are the Results?
- 6:33About the Start and Current Attitude
- 9:30How Does It Work?
- 13:53FL and EU AI Acts
- 17:13Good News
- 18:33Example
- 22:37Features
- 24:08Research
- 26:08Conclusions
- 27:36Q&A
related talks
31mFrom Theory to Practice: Advances in Real-World Federated Learning
42mFederated Learning: Unlocking the Values of Discrete Data for Enterprise
29mBalancing Thin Line Between Data Intelligence & Privacy
41mFederated Learning: Machine Learning on Decentralized Data
09mInterview with Blaise Aguéra y Arcas
30mFederated Learning from simulation to production
27mFederated Learning with Azure Machine Learning NVIDIA FLARE and MONAI
26mOpenFL (Federated Learning) Building better AI models with private data