Federated Imputation under Heterogeneous Feature Spaces
For federated learning practitioners dealing with tabular data where clients have partially overlapping feature sets, this work provides a method to perform imputation without requiring aligned feature schemas.
Federated imputation under heterogeneous feature spaces is addressed by FedHF-Impute, which uses a shared global feature graph and message passing to enable cross-client knowledge transfer even when features are never jointly observed locally. It improves RMSE by 26.9% on SECOM and 8.4% on AirQuality over FL baselines.
Federated Learning (FL) enables collaborative training across decentralized clients, but most methods assume aligned feature schemas, an assumption that rarely holds in tabular settings where clients observe only partially overlapping feature subsets. In these heterogeneous feature spaces, parameter-averaging methods (e.g., FedAvg) transfer little information across weakly overlapping or disjoint feature groups, limiting their effectiveness for federated imputation. To overcome this, we propose \textbf{FedHF-Impute}, a federated imputation framework that separates structural feature unavailability from conventional missingness and uses a shared global feature graph to propagate information across statistically related features through message passing. This enables indirect cross-client knowledge transfer, even when features are never jointly observed locally, while preserving standard federated communication. Under simulated partial schema overlap on the SECOM and AirQuality datasets, FedHF-Impute improves imputation accuracy (RMSE) over FL baselines by 26.9\%, and 8.4\% respectively, while achieving comparable performance on PhysioNET, with only a 0.3\% difference relative to the best baseline.