A federated framework uses per-client nonlinear state space models and a central graph attention network on latent states to learn and interpret cross-client temporal dynamics with convergence guarantees.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Federated Learning of Nonlinear Temporal Dynamics with Graph Attention-based Cross-Client Interpretability
A federated framework uses per-client nonlinear state space models and a central graph attention network on latent states to learn and interpret cross-client temporal dynamics with convergence guarantees.