解决跨客户端特征不一致下的数据补全问题，实现无直接重叠特征间的知识迁移。
Federated Imputation under Heterogeneous Feature Spaces
- 将缺失数据与特征缺失分离建模，通过全局特征图传递信息
- 在SECOM和AirQuality上比基线提升26.9%和8.4%的补全准确率
- 适用于特征部分重叠场景，适合医疗、工业等异构数据应用
联邦学习（FL）可在去中心化客户端间协作训练，但多数方法假设特征结构对齐，这在表格数据中通常不成立——各客户端仅观测到部分重叠的特征子集。在此异构特征空间下，参数平均方法（如FedAvg）在弱重叠或无重叠特征组间难以传递信息，限制了联邦补全效果。为此，我们提出FedHF-Impute框架，将结构特征缺失与常规缺失分离，并利用共享全局特征图，通过消息传递在统计相关特征间传播信息，实现间接跨客户端知识迁移，同时保持标准联邦通信机制。在SECOM和AirQuality数据集上模拟部分模式重叠时，该方法相比联邦基线分别提升26.9%和8.4%的补全准确率（RMSE），在PhysioNET上性能相当，仅比最优基线低0.3%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。