# Hybrid Federated Learning: Algorithms and Implementation

arXiv: https://arxiv.org/abs/2012.12420 · HTML: https://mlsanity.com/paper/2012.12420/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 14 of 14)

- [Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data](https://mlsanity.com/paper/2206.08330/) (2022)
- [A Hybrid Architecture for Federated and Centralized Learning](https://mlsanity.com/paper/2105.03288/) (2021)
- [Effective and Efficient Federated Tree Learning on Hybrid Data](https://mlsanity.com/paper/2310.11865/) (2023)
- [A Primal-Dual Algorithm for Hybrid Federated Learning](https://mlsanity.com/paper/2210.08106/) (2022)
- [A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning](https://mlsanity.com/paper/2309.09977/) (2023)
- [Federated and Transfer Learning for Cancer Detection Based on Image Analysis](https://mlsanity.com/paper/2405.20126/) (2024)
- [Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks](https://mlsanity.com/paper/2402.02225/) (2024)
- [Hybrid FedGraph: An efficient hybrid federated learning algorithm using graph convolutional neural network](https://mlsanity.com/paper/2404.09443/) (2024)
- [A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT](https://mlsanity.com/paper/2410.01644/) (2024)
- [Federated Automated Feature Engineering](https://mlsanity.com/paper/2412.04404/) (2024)
- [Scaling Probabilistic Circuits via Data Partitioning](https://mlsanity.com/paper/2503.08141/) (2025)
- [Comparative Evaluation of Data Decoupling Techniques for Federated Machine Learning with Database as a Service](https://mlsanity.com/paper/2303.08371/) (2023)
- [TablePuppet: A Generic Framework for Relational Federated Learning](https://mlsanity.com/paper/2403.15839/) (2024)
- [BlendFL: Blended Federated Learning for Handling Multimodal Data Heterogeneity](https://mlsanity.com/paper/2510.13266/) (2025)

## Abstract (arXiv)

Federated learning (FL) is a recently proposed distributed machine learning paradigm dealing with distributed and private data sets. Based on the data partition pattern, FL is often categorized into horizontal, vertical, and hybrid settings. Despite the fact that many works have been developed for the first two approaches, the hybrid FL setting (which deals with partially overlapped feature space and sample space) remains less explored, though this setting is extremely important in practice. In this paper, we first set up a new model-matching-based problem formulation for hybrid FL, then propose an efficient algorithm that can collaboratively train the global and local models to deal with full and partial featured data. We conduct numerical experiments on the multi-view ModelNet40 data set to validate the performance of the proposed algorithm. To the best of our knowledge, this is the first formulation and algorithm developed for the hybrid FL.