# FedEMA-Distill: Exponential Moving Average Guided Knowledge Distillation for Robust Federated Learning

arXiv: https://arxiv.org/abs/2603.04422 · HTML: https://mlsanity.com/paper/2603.04422/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Federated, robust and private distillation, one of 12 directions in Knowledge distillation.
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 15 Feb 2026.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (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)
- [Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data](https://mlsanity.com/paper/1811.11479/) (2018)
- [FedKD: Communication Efficient Federated Learning via Knowledge Distillation](https://mlsanity.com/paper/2108.13323/) (2021)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [SCAFFOLD: Stochastic Controlled Averaging for Federated Learning](https://mlsanity.com/paper/1910.06378/) (2019)
- [Federated Distillation: A Survey](https://mlsanity.com/paper/2404.08564/) (2024)
- [A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Data](https://mlsanity.com/paper/2309.01275/) (2023)
- [FedRAD: Federated Robust Adaptive Distillation](https://mlsanity.com/paper/2112.01405/) (2021)
- [On the Byzantine-Resilience of Distillation-Based Federated Learning](https://mlsanity.com/paper/2402.12265/) (2024)
- [FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving](https://mlsanity.com/paper/2505.00318/) (2025)
- [Federated Learning for 6G: Paradigms, Taxonomy, Recent Advances and Insights](https://mlsanity.com/paper/2312.04688/) (2023)
- [Efficient Collaborations through Weight-Driven Coalition Dynamics in Federated Learning Systems](https://mlsanity.com/paper/2401.12356/) (2024)

## Abstract (arXiv)

Federated learning (FL) often degrades when clients hold heterogeneous non-Independent and Identically Distributed (non-IID) data and when some clients behave adversarially, leading to client drift, slow convergence, and high communication overhead. This paper proposes FedEMA-Distill, a server-side procedure that combines an exponential moving average (EMA) of the global model with ensemble knowledge distillation from client-uploaded prediction logits evaluated on a small public proxy dataset. Clients run standard local training, upload only compressed logits, and may use different model architectures, so no changes are required to client-side software while still supporting model heterogeneity across devices. Experiments on CIFAR-10, CIFAR-100, FEMNIST, and AG News under Dirichlet-0.1 label skew show that FedEMA-Distill improves top-1 accuracy by several percentage points (up to +5% on CIFAR-10 and +6% on CIFAR-100) over representative baselines, reaches a given target accuracy in 30-35% fewer communication rounds, and reduces per-round client uplink payloads to 0.09-0.46 MB, i.e., roughly an order of magnitude less than transmitting full model weights. Using coordinate-wise median or trimmed-mean aggregation of logits at the server further stabilizes training in the presence of up to 10-20% Byzantine clients and yields well-calibrated predictions under attack. These results indicate that coupling temporal smoothing with logits-only aggregation provides a communication-efficient and attack-resilient FL pipeline that is deployment-friendly and compatible with secure aggregation and differential privacy, since only aggregated or obfuscated model outputs are exchanged.