MultiKrumFullModelAggregationStrategy<T, TInput, TOutput>
Models & Types · AiDotNet.FederatedLearning.Aggregators
Multi-Krum aggregation for IFullModel (select m central updates, then average).
Inheritance: FederatedLearningComponentBase<T> → AggregationStrategyBase<IFullModel<T, TInput, TOutput>, T> → RobustFullModelAggregationStrategyBase<T, TInput, TOutput> → MultiKrumFullModelAggregationStrategy<T, TInput, TOutput>
How It Works
For Beginners: Multi-Krum is like Krum, but instead of picking only one client update, it picks a small group of the most “central” updates and averages them.
Constructors
| Constructor | Summary |
|---|---|
MultiKrumFullModelAggregationStrategy(int byzantineClientCount, int selectionCount, bool useClientWeightsForAveraging) |
Methods
| Method | Summary |
|---|---|
IFullModel<T, TInput, TOutput> Aggregate(Dictionary<int, IFullModel<T, TInput, TOutput>> clientModels, Dictionary<int, double> clientWeights) |
|
string GetStrategyName() |