# Personalized Federated Learning via Stacking

arXiv: https://arxiv.org/abs/2404.10957 · HTML: https://mlsanity.com/paper/2404.10957/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 16 Apr 2024.

## Builds on (most cited first, 11 of 11)

- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Three Approaches for Personalization with Applications to Federated Learning](https://mlsanity.com/paper/2002.10619/) (2020)
- [Adaptive Gradient-Based Meta-Learning Methods](https://mlsanity.com/paper/1906.02717/) (2019)
- [A Survey on Homomorphic Encryption Schemes: Theory and Implementation](https://mlsanity.com/paper/1704.03578/) (2017)
- [Federated Meta-Learning with Fast Convergence and Efficient Communication](https://mlsanity.com/paper/1802.07876/) (2018)
- [BAGAN: Data Augmentation with Balancing GAN](https://mlsanity.com/paper/1803.09655/) (2018)
- [Robust Federated Learning in a Heterogeneous Environment](https://mlsanity.com/paper/1906.06629/) (2019)
- [WrapperFL: A Model Agnostic Plug-in for Industrial Federated Learning](https://mlsanity.com/paper/2206.10407/) (2022)

## Abstract (arXiv)

Traditional Federated Learning (FL) methods typically train a single global model collaboratively without exchanging raw data. In contrast, Personalized Federated Learning (PFL) techniques aim to create multiple models that are better tailored to individual clients' data. We present a novel personalization approach based on stacked generalization where clients directly send each other privacy-preserving models to be used as base models to train a meta-model on private data. Our approach is flexible, accommodating various privacy-preserving techniques and model types, and can be applied in horizontal, hybrid, and vertically partitioned federations. Additionally, it offers a natural mechanism for assessing each client's contribution to the federation. Through comprehensive evaluations across diverse simulated data heterogeneity scenarios, we showcase the effectiveness of our method.