Aug 2026· International Journal of Machine Learning and Cybernetics· Vol 17· 0 citations· 68 references
TL;DR
This work proposes FedHAttn, a novel hierarchical attention–based aggregation mechanism that explicitly models inter-client model feature importance to optimize global model performance and establishes an effective aggregator that balances accuracy, robustness, and efficiency in federated PM2.5 prediction.
This work proposes a data-Quality-aware aggregation framework by introducing an Evolutionary-computation-inspired de-sign into Federated learning ( FedEvoQ), with a lightweight dual-branch architecture.
FedTP is proposed, a federated learning framework that integrates gradient conflict elimination into the aggregation process and harmonizes local updates, thereby improving fairness across clients without compromising overall predictive accuracy.
Baobao Chai, Zhongyuan Yu, Tianqing He et al.· 0 citations
This paper proposes federated clustering with adaptive personalization (FedCAP), a parameter-efficient personalized FL framework that separates cluster-level representation learning from client-level adaptation.
Xingyu Tian, Citong Que, Faisal Nadeem Khan· Telecom· 0 citations
Experimental results on real-world energy consumption datasets demonstrate that the proposed FL framework achieves competitive forecasting accuracy while preserving client data privacy, and a rigorous comparative analysis reveals that FedProx and FedTrimmedAvg consistently outperform FedAvg under non-IID conditions.
A. Tibermacine, Ilyes Naidji, Imad Eddine Tibermacine et al.· Frontiers in Energy Research· 1 citation
Energy-Aware Adaptive Quantization and Freezing (EA-AQF), a unified framework that co-optimizes communication and computation, is presented, a unified framework that co-optimizes communication and computation and maintains robust convergence in highly heterogeneous tasks.
The Federated Green Anaconda Optimizer (FedGAO), an innovative FL framework inspired by the behavioral patterns of the Green Anaconda Optimizer (GAO), is proposed, demonstrating superior performance in terms of accuracy, convergence speed, and resource efficiency.
Elahe Eslami, S. A. Shahzadeh Fazeli, J. Abouei et al.· Cluster Computing· 0 citations