<ul><li>A new algorithm is proposed to mitigate model generalization loss in Vertical Federated Learning operating under client reliability constraints within 5G Core Networks.</li><li>The performance of Vertical Federated Learning degrades when Network Data Analytics Functions, primary clients for model training and inference, experience reliability issues in 5G Core Networks due to resource constraints and operational overhead.</li><li>Unlike edge environments, CN environments have centralized data orchestration capabilities, allowing for better distributed solutions utilizing the flexibility in data handling.</li><li>The proposed method optimizes vertical feature split among clients while centrally defining their local models based on reliability metrics, demonstrating improved performance over traditional baseline methods.</li></ul>

Reliable Vertical Federated Learning in 5G Core Network Architecture

Discover more