World models learn state evolution from trajectories, making access to temporal context a central training requirement.
Federated learning can use distributed records, while ownership boundaries within a trajectory restrict the examples each client can construct.
Our Study
Our study benchmarks this cross-time setting through hourly action-conditioned clinical prediction on eight MIMIC-IV disease cohorts, comprising 40.87 million transition memberships.
We specify severity-based client ownership, patient-separated construction, local history and future-window rules, and paired rollout evaluation from one to 32 hours.
A matrix of ten federated algorithms covers 32 disease--partition configurations under five rounds of ten-percent participation.
Findings
Three findings emerge from existing results and training logs.
- Client ownership and participation jointly restrict long-window coverage: only 7.55%--21.36% of pooled-available 32-step windows have a locally complete anchor visited during training, averaged across diseases.
- Finer severity partitions accompany higher FedAvg error in 15 of 16 paired comparisons, while algorithm gains are small and horizon-dependent: FedProx reduces mean error by 0.56%, with no consistent improvement at 32 steps.
- Algorithm labels conceal distinct update behavior, including inactive extrapolation and orders-of-magnitude differences in update scale. Cached-update performance also varies strongly across trajectory partitions under the same benchmark protocol.
These results establish temporal access, participation coverage, optimization behavior, and horizon-resolved prediction as complementary dimensions for evaluating federated clinical world models.