# Federated Learning with Hypergradient-based Online Update of Aggregation Weights

arXiv: https://arxiv.org/abs/2605.00458 · HTML: https://mlsanity.com/paper/2605.00458/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 13 of 13)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Bayesian Nonparametric Federated Learning of Neural Networks](https://mlsanity.com/paper/1905.12022/) (2019)
- [Online Learning Rate Adaptation with Hypergradient Descent](https://mlsanity.com/paper/1703.04782/) (2017)
- [Fast-Convergent Federated Learning with Adaptive Weighting](https://mlsanity.com/paper/2012.00661/) (2020)
- [Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework](https://mlsanity.com/paper/2002.10671/) (2020)
- [Revisiting Weighted Aggregation in Federated Learning with Neural Networks](https://mlsanity.com/paper/2302.10911/) (2023)
- [Federated Learning: A Signal Processing Perspective](https://mlsanity.com/paper/2103.17150/) (2021)
- [FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent](https://mlsanity.com/paper/2310.03156/) (2023)
- [FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking](https://mlsanity.com/paper/2503.15111/) (2025)
- [Federated Learning with Erroneous Communication Links](https://mlsanity.com/paper/2201.12991/) (2022)

## Abstract (arXiv)

Federated learning using mobile and Internet of Things devices requires not only the ability to handle heterogeneity of clients' data distributions but also high adaptability to varying communication environments. We propose FedHAW (Federated Learning with Hypergradient-based update of Aggregation Weights) that implements online updates of aggregation weights. FedHAW updates the aggregation weights by using hypergradient, the gradient of the objective function with respect to the weights, which can be calculated with low computational overhead. Simulation results show that the proposed method possesses high generalization performance in heterogeneous environments and high robustness to communication errors.