FedGAug: Diagnosing Late-Onset Instability in Graph-Augmented Federated Clinical Prediction

Federated learning (FL) lets hospitals train clinical prediction models together without pooling their electronic health records (EHRs). When patient populations differ between sites, however, the aggregated global model can break down after many communication rounds. We present FedGAug, a federated clinical prediction system that pairs a parameter-efficient transformer with a per-patient knowledge graph encoder, where each local graph is enriched with entities retrieved from external biomedical sources. We train it on three non-IID clients with three random seeds each, using asynchronous, staleness-weighted FedAvg. Without regularization, the global model improves steadily to a mean AUROC of $0.907$ at round 12 and shows no forgetting up to that point. It then collapses to $0.370$ by round 15 and stays there until round 20. Evaluating the local and global models separately shows that the local models hold up much better (AUROC around $0.71$ against $0.37$ for the global model during the collapse), which points to aggregation rather than local overfitting as the source of the failure. We then test Elastic Weight Consolidation (EWC) and Knowledge Distillation (KD) as remedies. None of the regularized variants collapses. Over 29 rounds their peak-to-final forgetting stays at or below $0.005$, compared with $0.169$ for the unregularized model, and EWC with $\lambda =0.5$ still reaches a mean AUROC of $0.856$ at round 21, when the unregularized model is at $0.385$. Our results show that late-onset degradation in non-IID federated clinical prediction can originate at the aggregation step, and that continual-learning regularization prevents it over long training runs.