All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
- Initial release
FlattenedModelclass for parameter flattening/unflatteningMaskdataclass for efficient binary mask representationMaskSelectorabstract base class with implementations:RandomMaskSelector: Per-round random selectionTopKMagnitudeSelector: Magnitude-based selectionGradientBasedSelector: Gradient-magnitude selectionStructuredMaskSelector: Layer-aware selectionFixedMaskSelector: User-defined indicesClientSpecificMaskSelector: Per-client different masks
- Flower integration:
PSFedAvgstrategyPSFedClientbase class
- Examples:
- MNIST basic example
- CIFAR-10 advanced example
- Comprehensive test suite
- Documentation
- N/A
- N/A
- N/A
- N/A
- N/A