# The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation

arXiv: https://arxiv.org/abs/2301.08968 · HTML: https://mlsanity.com/paper/2301.08968/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Federated, robust and private distillation, one of 12 directions in Knowledge distillation.
- Builds on 52 of its 67 references that are in the map.
- First posted on arXiv 21 Jan 2023.

## Placed in

- Knowledge distillation / [Federated, robust and private distillation](https://mlsanity.com/distill/federated-robust-and-private-distillation/)

## Builds on (most cited first, 30 of 52)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Bayesian Nonparametric Federated Learning of Neural Networks](https://mlsanity.com/paper/1905.12022/) (2019)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [Adaptive Personalized Federated Learning](https://mlsanity.com/paper/2003.13461/) (2020)
- [Three Approaches for Personalization with Applications to Federated Learning](https://mlsanity.com/paper/2002.10619/) (2020)

## Built on by (most cited first, 25 of 25)

- [Multimodal Federated Learning with Missing Modality via Prototype Mask and Contrast](https://mlsanity.com/paper/2312.13508/) (2023)
- [Federated Distillation: A Survey](https://mlsanity.com/paper/2404.08564/) (2024)
- [Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices](https://mlsanity.com/paper/2311.18129/) (2023)
- [ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning](https://mlsanity.com/paper/2310.05143/) (2023)
- [Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions](https://mlsanity.com/paper/2406.10861/) (2024)
- [Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2312.13923/) (2023)
- [Federated Learning on Virtual Heterogeneous Data with Local-global Distillation](https://mlsanity.com/paper/2303.02278/) (2023)
- [Subgraph Federated Learning for Local Generalization](https://mlsanity.com/paper/2503.03995/) (2025)
- [Little is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning](https://mlsanity.com/paper/2310.05696/) (2023)
- [Recovering Labels from Local Updates in Federated Learning](https://mlsanity.com/paper/2405.00955/) (2024)
- [FedD2S: Personalized Data-Free Federated Knowledge Distillation](https://mlsanity.com/paper/2402.10846/) (2024)
- [SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments](https://mlsanity.com/paper/2405.04875/) (2024)
- [Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning](https://mlsanity.com/paper/2310.00198/) (2023)
- [Optimal Transceiver Design in Over-the-Air Federated Distillation](https://mlsanity.com/paper/2507.15256/) (2025)
- [Collaborative Adaptive Curriculum for Progressive Knowledge Distillation](https://mlsanity.com/paper/2603.20296/) (2026)
- [Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignment](https://mlsanity.com/paper/2311.04818/) (2023)
- [Variational Bayes for Federated Continual Learning](https://mlsanity.com/paper/2405.14291/) (2024)
- [On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach](https://mlsanity.com/paper/2508.02993/) (2025)
- [CDFL: Efficient Federated Human Activity Recognition using Contrastive Learning and Deep Clustering](https://mlsanity.com/paper/2407.12287/) (2024)
- [Unveiling Client Privacy Leakage from Public Dataset Usage in Federated Distillation](https://mlsanity.com/paper/2502.08001/) (2025)
- [WarmFed: Federated Learning with Warm-Start for Globalization and Personalization Via Personalized Diffusion Models](https://mlsanity.com/paper/2503.03110/) (2025)
- [Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks](https://mlsanity.com/paper/2504.00540/) (2025)
- [FedMP: Tackling Medical Feature Heterogeneity in Federated Learning from a Manifold Perspective](https://mlsanity.com/paper/2508.09174/) (2025)
- [FedeCouple: Fine-Grained Balancing of Global-Generalization and Local-Adaptability in Federated Learning](https://mlsanity.com/paper/2511.09599/) (2025)
- [Multimodal QUD: Inquisitive Questions from Scientific Figures](https://mlsanity.com/paper/2604.23733/) (2026)

## Abstract (arXiv)

Heterogeneity of data distributed across clients limits the performance of global models trained through federated learning, especially in the settings with highly imbalanced class distributions of local datasets. In recent years, personalized federated learning (pFL) has emerged as a potential solution to the challenges presented by heterogeneous data. However, existing pFL methods typically enhance performance of local models at the expense of the global model's accuracy. We propose FedHKD (Federated Hyper-Knowledge Distillation), a novel FL algorithm in which clients rely on knowledge distillation (KD) to train local models. In particular, each client extracts and sends to the server the means of local data representations and the corresponding soft predictions -- information that we refer to as ``hyper-knowledge". The server aggregates this information and broadcasts it to the clients in support of local training. Notably, unlike other KD-based pFL methods, FedHKD does not rely on a public dataset nor it deploys a generative model at the server. We analyze convergence of FedHKD and conduct extensive experiments on visual datasets in a variety of scenarios, demonstrating that FedHKD provides significant improvement in both personalized as well as global model performance compared to state-of-the-art FL methods designed for heterogeneous data settings.