Comparative Analysis of FlexLoRA and FedAvg for GLUE Cross-Domain Accuracy Under Non-IID Data Distributions

Federated learning (FL) has recently emerged as a popular privacy-preserving collaborative learning paradigm. However, it suffers from the non-independent and identically distributed (non-IID) data among clients. In this paper, we propose a novel framework, named Synthetic Data Aided Federated Learning (SDA-FL), to resolve this non-IID challenge by sharing synthetic data. Specifically, each client pretrains a local generative adversarial network (GAN) to generate differentially private synthetic data, which are uploaded to the parameter server (PS) to construct a global shared synthetic datase

Research goal: How does FlexLoRA's aggregation scheme compare to FedAvg in maintaining accuracy on GLUE cross-domain tasks under non-IID data distributions?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.5/10.