# Ensemble Distillation for Robust Model Fusion in Federated Learning

arXiv: https://arxiv.org/abs/2006.07242 · HTML: https://mlsanity.com/paper/2006.07242/

## Key facts

- Cited by 682 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2020.

## Built on by (most cited first, 30 of 682)

- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [A Field Guide to Federated Optimization](https://mlsanity.com/paper/2107.06917/) (2021)
- [Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models](https://mlsanity.com/paper/2305.18292/) (2023)
- [No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2106.05001/) (2021)
- [FedKD: Communication Efficient Federated Learning via Knowledge Distillation](https://mlsanity.com/paper/2108.13323/) (2021)
- [Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning](https://mlsanity.com/paper/2203.09249/) (2022)
- [Heterogeneous Federated Learning: State-of-the-art and Research Challenges](https://mlsanity.com/paper/2307.10616/) (2023)
- [Generalized Federated Learning via Sharpness Aware Minimization](https://mlsanity.com/paper/2206.02618/) (2022)
- [Federated Learning from Pre-Trained Models: A Contrastive Learning Approach](https://mlsanity.com/paper/2209.10083/) (2022)
- [Distributed Learning in Wireless Networks: Recent Progress and Future Challenges](https://mlsanity.com/paper/2104.02151/) (2021)
- [FedALA: Adaptive Local Aggregation for Personalized Federated Learning](https://mlsanity.com/paper/2212.01197/) (2022)
- [Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning](https://mlsanity.com/paper/2108.10241/) (2021)
- [Multi-Center Federated Learning: Clients Clustering for Better Personalization](https://mlsanity.com/paper/2108.08647/) (2021)
- [Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2106.06047/) (2021)
- [Parameterized Knowledge Transfer for Personalized Federated Learning](https://mlsanity.com/paper/2111.02862/) (2021)
- [Federated Learning with Label Distribution Skew via Logits Calibration](https://mlsanity.com/paper/2209.00189/) (2022)
- [FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction](https://mlsanity.com/paper/2212.01548/) (2022)
- [DENSE: Data-Free One-Shot Federated Learning](https://mlsanity.com/paper/2112.12371/) (2021)
- [Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark](https://mlsanity.com/paper/2311.06750/) (2023)
- [Improving Generalization in Federated Learning by Seeking Flat Minima](https://mlsanity.com/paper/2203.11834/) (2022)
- [Personalized Federated Learning with Feature Alignment and Classifier Collaboration](https://mlsanity.com/paper/2306.11867/) (2023)
- [Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources](https://mlsanity.com/paper/2402.11505/) (2024)
- [Deep Model Fusion: A Survey](https://mlsanity.com/paper/2309.15698/) (2023)
- [Preservation of the Global Knowledge by Not-True Distillation in Federated Learning](https://mlsanity.com/paper/2106.03097/) (2021)
- [Multimodal Federated Learning via Contrastive Representation Ensemble](https://mlsanity.com/paper/2302.08888/) (2023)
- [Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning](https://mlsanity.com/paper/2204.12703/) (2022)

## Abstract (arXiv)

Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. However, directly averaging model parameters is only possible if all models have the same structure and size, which could be a restrictive constraint in many scenarios. In this work we investigate more powerful and more flexible aggregation schemes for FL. Specifically, we propose ensemble distillation for model fusion, i.e. training the central classifier through unlabeled data on the outputs of the models from the clients. This knowledge distillation technique mitigates privacy risk and cost to the same extent as the baseline FL algorithms, but allows flexible aggregation over heterogeneous client models that can differ e.g. in size, numerical precision or structure. We show in extensive empirical experiments on various CV/NLP datasets (CIFAR-10/100, ImageNet, AG News, SST2) and settings (heterogeneous models/data) that the server model can be trained much faster, requiring fewer communication rounds than any existing FL technique so far.