VARS-FL builds client reputation from validation loss reduction signals and uses sliding-window averaging plus log-scaled participation to select clients, yielding up to 36% faster convergence to 80% accuracy on non-IID Edge-IIoTset intrusion detection.
Advances and open problems in federated learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
EdgeDetect delivers 98% multi-class accuracy in federated intrusion detection with 32x gradient compression via median binarization and homomorphic encryption, cutting per-round communication from 450 MB to 14 MB.
Introduces incentive-aware federated averaging with NE-seeking dataset size updates and establishes performance guarantees plus asymptotic convergence for strategic participation in convex, nonconvex, and monotone settings.
citing papers explorer
-
VARS-FL: Validation-Aligned Client Selection for Non-IID Federated Learning in IoT Systems
VARS-FL builds client reputation from validation loss reduction signals and uses sliding-window averaging plus log-scaled participation to select clients, yielding up to 36% faster convergence to 80% accuracy on non-IID Edge-IIoTset intrusion detection.
-
EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection
EdgeDetect delivers 98% multi-class accuracy in federated intrusion detection with 32x gradient compression via median binarization and homomorphic encryption, cutting per-round communication from 450 MB to 14 MB.
-
Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participation
Introduces incentive-aware federated averaging with NE-seeking dataset size updates and establishes performance guarantees plus asymptotic convergence for strategic participation in convex, nonconvex, and monotone settings.