# Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization

arXiv: https://arxiv.org/abs/2405.18890 · HTML: https://mlsanity.com/paper/2405.18890/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 53 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://mlsanity.com/paper/2207.07601/) (2022)
- [The Non-IID Data Quagmire of Decentralized Machine Learning](https://mlsanity.com/paper/1910.00189/) (2019)
- [Surrogate Gap Minimization Improves Sharpness-Aware Training](https://mlsanity.com/paper/2203.08065/) (2022)
- [Towards Understanding Sharpness-Aware Minimization](https://mlsanity.com/paper/2206.06232/) (2022)
- [Generalized Federated Learning via Sharpness Aware Minimization](https://mlsanity.com/paper/2206.02618/) (2022)
- [Efficient Sharpness-aware Minimization for Improved Training of Neural Networks](https://mlsanity.com/paper/2110.03141/) (2021)
- [Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning](https://mlsanity.com/paper/2202.03599/) (2022)
- [Sharpness-Aware Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2303.10353/) (2023)
- [Improving Generalization in Federated Learning by Seeking Flat Minima](https://mlsanity.com/paper/2203.11834/) (2022)
- [Sharpness-Aware Training for Free](https://mlsanity.com/paper/2205.14083/) (2022)
- [Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning](https://mlsanity.com/paper/2103.02148/) (2021)
- [FedCM: Federated Learning with Client-level Momentum](https://mlsanity.com/paper/2106.10874/) (2021)
- [Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach](https://mlsanity.com/paper/2210.05177/) (2022)
- [Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization](https://mlsanity.com/paper/2303.03108/) (2023)
- [FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy](https://mlsanity.com/paper/2302.10429/) (2023)

## Built on by (most cited first, 28 of 28)

- [FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models](https://mlsanity.com/paper/2406.04845/) (2024)
- [FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging](https://mlsanity.com/paper/2507.20016/) (2025)
- [FedMuon: Accelerating Federated Learning with Matrix Orthogonalization](https://mlsanity.com/paper/2510.27403/) (2025)
- [FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models](https://mlsanity.com/paper/2510.27486/) (2025)
- [Diversified Batch Selection for Training Acceleration](https://mlsanity.com/paper/2406.04872/) (2024)
- [Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters](https://mlsanity.com/paper/2406.09679/) (2024)
- [DC-Merge: Improving Model Merging with Directional Consistency](https://mlsanity.com/paper/2603.06242/) (2026)
- [Federated Domain Generalization with Data-free On-server Matching Gradient](https://mlsanity.com/paper/2501.14653/) (2025)
- [Federated Learning for Diffusion Models](https://mlsanity.com/paper/2503.06426/) (2025)
- [FedNSAM:Consistency of Local and Global Flatness for Federated Learning](https://mlsanity.com/paper/2602.23827/) (2026)
- [FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2510.20250/) (2025)
- [Federated ADMM from Bayesian Duality](https://mlsanity.com/paper/2506.13150/) (2025)
- [A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs](https://mlsanity.com/paper/2409.18915/) (2024)
- [FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysis](https://mlsanity.com/paper/2501.13967/) (2025)
- [FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification](https://mlsanity.com/paper/2511.12044/) (2025)
- [Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogeneous Federated Learning](https://mlsanity.com/paper/2503.11151/) (2025)
- [FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios](https://mlsanity.com/paper/2507.14980/) (2025)
- [Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization](https://mlsanity.com/paper/2602.11584/) (2026)
- [Neighborhood and Global Perturbations Supported SAM in Federated Learning: From Local Tweaks To Global Awareness](https://mlsanity.com/paper/2408.14144/) (2024)
- [DP2-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization](https://mlsanity.com/paper/2409.13645/) (2024)
- [Communication-Efficient Distributed Training for Collaborative Flat Optima Recovery in Deep Learning](https://mlsanity.com/paper/2507.20424/) (2025)
- [LSAM: Asynchronous Distributed Training with Landscape-Smoothed Sharpness-Aware Minimization](https://mlsanity.com/paper/2509.03110/) (2025)
- [Why Federated Optimization Fails to Achieve Perfect Fitting? A Theoretical Perspective on Client-Side Optima](https://mlsanity.com/paper/2511.00469/) (2025)
- [FedSCAM (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation): Scam-resistant SAM for Robust Federated Optimization in Heterogeneous Environments](https://mlsanity.com/paper/2601.00853/) (2025)
- [Beyond Fixed Rounds: Data-Free Early Stopping for Practical Federated Learning](https://mlsanity.com/paper/2601.22669/) (2026)
- [FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning](https://mlsanity.com/paper/2605.09144/) (2026)
- [FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering](https://mlsanity.com/paper/2607.04170/) (2026)
- [SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity](https://mlsanity.com/paper/2607.04189/) (2026)

## Abstract (arXiv)

In federated learning (FL), the multi-step update and data heterogeneity among clients often lead to a loss landscape with sharper minima, degenerating the performance of the resulted global model. Prevalent federated approaches incorporate sharpness-aware minimization (SAM) into local training to mitigate this problem. However, the local loss landscapes may not accurately reflect the flatness of global loss landscape in heterogeneous environments; as a result, minimizing local sharpness and calculating perturbations on client data might not align the efficacy of SAM in FL with centralized training. To overcome this challenge, we propose FedLESAM, a novel algorithm that locally estimates the direction of global perturbation on client side as the difference between global models received in the previous active and current rounds. Besides the improved quality, FedLESAM also speed up federated SAM-based approaches since it only performs once backpropagation in each iteration. Theoretically, we prove a slightly tighter bound than its original FedSAM by ensuring consistent perturbation. Empirically, we conduct comprehensive experiments on four federated benchmark datasets under three partition strategies to demonstrate the superior performance and efficiency of FedLESAM.