# Global Update Guided Federated Learning

arXiv: https://arxiv.org/abs/2204.03920 · HTML: https://mlsanity.com/paper/2204.03920/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 8 Apr 2022.

## Builds on (most cited first, 10 of 10)

- [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: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Overcoming Forgetting in Federated Learning on Non-IID Data](https://mlsanity.com/paper/1910.07796/) (2019)
- [Graph-Based Spatial-Temporal Convolutional Network for Vehicle Trajectory Prediction in Autonomous Driving](https://mlsanity.com/paper/2109.12764/) (2021)
- [Continual Local Training for Better Initialization of Federated Models](https://mlsanity.com/paper/2005.12657/) (2020)
- [A Cooperation-Aware Lane Change Method for Autonomous Vehicles](https://mlsanity.com/paper/2201.10746/) (2022)

## Built on by (most cited first, 2 of 2)

- [FedMap: Iterative Magnitude-Based Pruning for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2406.19050/) (2024)
- [Sybil-based Virtual Data Poisoning Attacks in Federated Learning](https://mlsanity.com/paper/2505.09983/) (2025)

## Abstract (arXiv)

Federated learning protects data privacy and security by exchanging models instead of data. However, unbalanced data distributions among participating clients compromise the accuracy and convergence speed of federated learning algorithms. To alleviate this problem, unlike previous studies that limit the distance of updates for local models, we propose global-update-guided federated learning (FedGG), which introduces a model-cosine loss into local objective functions, so that local models can fit local data distributions under the guidance of update directions of global models. Furthermore, considering that the update direction of a global model is informative in the early stage of training, we propose adaptive loss weights based on the update distances of local models. Numerical simulations show that, compared with other advanced algorithms, FedGG has a significant improvement on model convergence accuracies and speeds. Additionally, compared with traditional fixed loss weights, adaptive loss weights enable our algorithm to be more stable and easier to implement in practice.