# Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning

arXiv: https://arxiv.org/abs/2507.10348 · HTML: https://mlsanity.com/paper/2507.10348/

## Key facts

- Cited by 5 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 35 of its 57 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## 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 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)
- [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)
- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning](https://mlsanity.com/paper/2203.09249/) (2022)
- [One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation](https://mlsanity.com/paper/2310.19444/) (2023)
- [TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation](https://mlsanity.com/paper/2303.06937/) (2023)
- [Peer Collaborative Learning for Online Knowledge Distillation](https://mlsanity.com/paper/2006.04147/) (2020)
- [No One Left Behind: Real-World Federated Class-Incremental Learning](https://mlsanity.com/paper/2302.00903/) (2023)
- [Federated Learning for Computationally-Constrained Heterogeneous Devices: A Survey](https://mlsanity.com/paper/2307.09182/) (2023)
- [Towards Efficient Replay in Federated Incremental Learning](https://mlsanity.com/paper/2403.05890/) (2024)
- [VkD: Improving Knowledge Distillation using Orthogonal Projections](https://mlsanity.com/paper/2403.06213/) (2024)
- [Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher](https://mlsanity.com/paper/2304.01731/) (2023)
- [Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey](https://mlsanity.com/paper/2412.13840/) (2024)

## Built on by (most cited first, 5 of 5)

- [Federated Language Models Under Bandwidth Budgets: Distillation Rates and Conformal Coverage](https://mlsanity.com/paper/2605.09986/) (2026)
- [Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning](https://mlsanity.com/paper/2509.22700/) (2025)
- [HARMONY: Bridging the Personalization-Generalization Gap by Mitigating Representation Skew in Heterogeneous Split Federated Learning](https://mlsanity.com/paper/2605.07211/) (2026)
- [Matching Rates and Optimal Allocation for Federated Probe-Logit Distillation under Heterogeneous Bandwidth Budgets](https://mlsanity.com/paper/2605.29642/) (2026)
- [SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning](https://mlsanity.com/paper/2607.19384/) (2026)

## Abstract (arXiv)

Model-Heterogeneous Federated Learning (Hetero-FL) has attracted growing attention for its ability to aggregate knowledge from heterogeneous models while keeping private data locally. To better aggregate knowledge from clients, ensemble distillation, as a widely used and effective technique, is often employed after global aggregation to enhance the performance of the global model. However, simply combining Hetero-FL and ensemble distillation does not always yield promising results and can make the training process unstable. The reason is that existing methods primarily focus on logit distillation, which, while being model-agnostic with softmax predictions, fails to compensate for the knowledge bias arising from heterogeneous models. To tackle this challenge, we propose a stable and efficient Feature Distillation for model-heterogeneous Federated learning, dubbed FedFD, that can incorporate aligned feature information via orthogonal projection to integrate knowledge from heterogeneous models better. Specifically, a new feature-based ensemble federated knowledge distillation paradigm is proposed. The global model on the server needs to maintain a projection layer for each client-side model architecture to align the features separately. Orthogonal techniques are employed to re-parameterize the projection layer to mitigate knowledge bias from heterogeneous models and thus maximize the distilled knowledge. Extensive experiments show that FedFD achieves superior performance compared to state-of-the-art methods.