Impact of Federated Learning Data Heterogeneity on Llama-3.1 Security Flaw Identification Accuracy

Federated Learning (FL) enables decentralized training of machine learning models on distributed data while preserving privacy. However, in real-world FL settings, client data is often non-identically distributed and imbalanced, resulting in statistical data heterogeneity which impacts the generalization capabilities of the server's model across clients, slows convergence and reduces performance. In this paper, we address this challenge by proposing first a characterization of statistical data heterogeneity by means of 6 metrics of global and client attribute imbalance, class imbalance, and sp

Research goal: What is the impact of federated learning data heterogeneity on the security flaw identification accuracy of Llama-3.1 versus centralized training baselines?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.7/10.