202604.20
IEEE Internet of Things Journal
CEHGLS: A Communication-Efficient Head Gradient Linear Search for Personalized Federated Learning Under Data Heterogeneity
Paper ↗Privacy & Security
PROFILE
Improve algorithms for data heterogeneity in federated learning to solve the Non‑IID problem of client data distribution. By combining global model sharing with local personalized optimization, each client can obtain a model adapted to its own data features while protecting data privacy.
Keywords: optimization algorithm, model aggregation, federated learning
None