CAEFL: Composable and Environment Aware Federated Learning Models
summary
CAEFL implements environment-aware federated learning in Elixir, using pattern matching tags from sensor behaviors to group updates and a parameter server that matches tagged push/pull requests and composes specialized or composite models. It uses on-device local training, selects top-R model updates (e.g. top 10%) for composition, and supports hot-code-swapping and transparent distribution on the BEAM. The implementation reports a 7–10% accuracy gain on MNIST and 2% on FashionMNIST versus standard federated averaging.
AI-written summary · about
chapters (6)
- 0:00Start
- 1:20What is Federated Learning?
- 3:02Motivation
- 28:36Experiment Results
- 33:18Conclusion
- 34:59Future Researches
related talks
42mFederated Learning: Unlocking the Values of Discrete Data for Enterprise
13mScalable and Portable Federated Learning Simulation Engine
41mFederated Learning: Machine Learning on Decentralized Data
31mFrom Theory to Practice: Advances in Real-World Federated Learning
42mLearning Together, Distributed: An Introduction to Federated Learning
48mFederated ML for Edge Applications
38mFederated Learning and Its Application...
25mData collaboration with Federated Learning