# Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning

arXiv: https://arxiv.org/abs/2407.03247 · HTML: https://mlsanity.com/paper/2407.03247/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2024.

## Built on by (most cited first, 11 of 11)

- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection](https://mlsanity.com/paper/2408.09227/) (2024)
- [HeteroTune: Efficient Federated Learning for Large Heterogeneous Models](https://mlsanity.com/paper/2411.16796/) (2024)
- [Asymmetrical Reciprocity-based Federated Learning for Resolving Disparities in Medical Diagnosis](https://mlsanity.com/paper/2412.19654/) (2024)
- [Membership Inference Attacks with False Discovery Rate Control](https://mlsanity.com/paper/2508.07066/) (2025)
- [Distilling A Universal Expert from Clustered Federated Learning](https://mlsanity.com/paper/2506.20285/) (2025)
- [Bridging Generalization Gap of Heterogeneous Federated Clients Using Generative Models](https://mlsanity.com/paper/2508.01669/) (2025)
- [FERA: Uncertainty-Aware Federated Reasoning for Large Language Models](https://mlsanity.com/paper/2605.10082/) (2026)
- [Stragglers Can Contribute More: Uncertainty-Aware Distillation for Asynchronous Federated Learning](https://mlsanity.com/paper/2511.19966/) (2025)
- [FedeKD: Energy-Based Gating for Robust Federated Knowledge Distillation under Heterogeneous Settings](https://mlsanity.com/paper/2605.05553/) (2026)
- [From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning](https://mlsanity.com/paper/2605.05959/) (2026)

## Abstract (arXiv)

This paper presents FedType, a simple yet pioneering framework designed to fill research gaps in heterogeneous model aggregation within federated learning (FL). FedType introduces small identical proxy models for clients, serving as agents for information exchange, ensuring model security, and achieving efficient communication simultaneously. To transfer knowledge between large private and small proxy models on clients, we propose a novel uncertainty-based asymmetrical reciprocity learning method, eliminating the need for any public data. Comprehensive experiments conducted on benchmark datasets demonstrate the efficacy and generalization ability of FedType across diverse settings. Our approach redefines federated learning paradigms by bridging model heterogeneity, eliminating reliance on public data, prioritizing client privacy, and reducing communication costs.