Federated Imputation under Heterogeneous Feature Spaces
Not on the map. Why?
Abstract (arXiv)
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 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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 46 references that are in the map. First posted on arXiv 15 May 2026.
Builds on
25 of 46 references.
References · 25
- 2017Attention Is All You Needcited by 60,361
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2021Model-Contrastive Federated Learningcited by 766
- 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
- 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 409
- 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
- 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
- 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
- 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
- 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
- 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
13 more
- 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 95
- 2022FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Datacited by 50
- 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
- 2023Learning from data with structured missingnesscited by 24
- 2022Vertical Federated Learning: A Structured Literature Reviewcited by 17
- 2024FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularizationcited by 16
- 2022Data Imputation with Iterative Graph Reconstructioncited by 15
- 2024Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchorcited by 9
- 2025Multimodal Federated Learning With Missing Modalities through Feature Imputation Networkcited by 8
- 2023Personalised Federated Learning On Heterogeneous Feature Spacescited by 5
- 2021SecureBoost+: Large Scale and High-Performance Vertical Federated Gradient Boosting Decision Treecited by 2
- 2023Fed-MIWAE: Federated Imputation of Incomplete Data via Deep Generative Modelscited by 2
- 2025FedSparQ: Adaptive Sparse Quantization with Error Feedback for Robust & Efficient Federated Learningcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.