# What Do We Mean by Generalization in Federated Learning?

arXiv: https://arxiv.org/abs/2110.14216 · HTML: https://mlsanity.com/paper/2110.14216/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 77 of its 105 references that are in the map.
- First posted on arXiv 27 Oct 2021.

## Builds on (most cited first, 30 of 77)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [Local SGD Converges Fast and Communicates Little](https://mlsanity.com/paper/1805.09767/) (2018)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Importance Weighted Autoencoders](https://mlsanity.com/paper/1509.00519/) (2015)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications](https://mlsanity.com/paper/1701.05517/) (2017)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [A Unified Theory of Decentralized SGD with Changing Topology and Local Updates](https://mlsanity.com/paper/2003.10422/) (2020)
- [Adaptive Personalized Federated Learning](https://mlsanity.com/paper/2003.13461/) (2020)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)

## Built on by (most cited first, 30 of 62)

- [Generalized Federated Learning via Sharpness Aware Minimization](https://mlsanity.com/paper/2206.02618/) (2022)
- [Plex: Towards Reliability using Pretrained Large Model Extensions](https://mlsanity.com/paper/2207.07411/) (2022)
- [Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark](https://mlsanity.com/paper/2311.06750/) (2023)
- [Improving Generalization in Federated Learning by Seeking Flat Minima](https://mlsanity.com/paper/2203.11834/) (2022)
- [Federated Learning on Non-IID Graphs via Structural Knowledge Sharing](https://mlsanity.com/paper/2211.13009/) (2022)
- [FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning](https://mlsanity.com/paper/2302.13485/) (2023)
- [No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier](https://mlsanity.com/paper/2303.10058/) (2023)
- [pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning](https://mlsanity.com/paper/2206.03655/) (2022)
- [Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective](https://mlsanity.com/paper/2111.03741/) (2021)
- [Efficient Personalized Federated Learning via Sparse Model-Adaptation](https://mlsanity.com/paper/2305.02776/) (2023)
- [Motley: Benchmarking Heterogeneity and Personalization in Federated Learning](https://mlsanity.com/paper/2206.09262/) (2022)
- [Accelerated Federated Learning with Decoupled Adaptive Optimization](https://mlsanity.com/paper/2207.07223/) (2022)
- [Gradient Masked Averaging for Federated Learning](https://mlsanity.com/paper/2201.11986/) (2022)
- [FedFA: Federated Feature Augmentation](https://mlsanity.com/paper/2301.12995/) (2023)
- [FedImpro: Measuring and Improving Client Update in Federated Learning](https://mlsanity.com/paper/2402.07011/) (2024)
- [Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning](https://mlsanity.com/paper/2206.02604/) (2022)
- [Benchmarking Algorithms for Federated Domain Generalization](https://mlsanity.com/paper/2307.04942/) (2023)
- [FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection](https://mlsanity.com/paper/2410.11397/) (2024)
- [Federated Learning with Bilateral Curation for Partially Class-Disjoint Data](https://mlsanity.com/paper/2405.18972/) (2024)
- [FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion](https://mlsanity.com/paper/2410.20380/) (2024)
- [Auxo: Efficient Federated Learning via Scalable Client Clustering](https://mlsanity.com/paper/2210.16656/) (2022)
- [Making Batch Normalization Great in Federated Deep Learning](https://mlsanity.com/paper/2303.06530/) (2023)
- [On Noisy Evaluation in Federated Hyperparameter Tuning](https://mlsanity.com/paper/2212.08930/) (2022)
- [Federated Learning under Covariate Shifts with Generalization Guarantees](https://mlsanity.com/paper/2306.05325/) (2023)
- [PraFFL: A Preference-Aware Scheme in Fair Federated Learning](https://mlsanity.com/paper/2404.08973/) (2024)
- [Federated brain tumor segmentation: an extensive benchmark](https://mlsanity.com/paper/2410.17265/) (2024)
- [FAA-CLIP: Federated Adversarial Adaptation of CLIP](https://mlsanity.com/paper/2503.05776/) (2025)
- [Wasserstein Distributionally Robust Optimization with Wasserstein Barycenters](https://mlsanity.com/paper/2203.12136/) (2022)
- [Towards Understanding Generalization and Stability Gaps between Centralized and Decentralized Federated Learning](https://mlsanity.com/paper/2310.03461/) (2023)
- [FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning](https://mlsanity.com/paper/2401.02734/) (2024)

## Abstract (arXiv)

Federated learning data is drawn from a distribution of distributions: clients are drawn from a meta-distribution, and their data are drawn from local data distributions. Thus generalization studies in federated learning should separate performance gaps from unseen client data (out-of-sample gap) from performance gaps from unseen client distributions (participation gap). In this work, we propose a framework for disentangling these performance gaps. Using this framework, we observe and explain differences in behavior across natural and synthetic federated datasets, indicating that dataset synthesis strategy can be important for realistic simulations of generalization in federated learning. We propose a semantic synthesis strategy that enables realistic simulation without naturally-partitioned data. Informed by our findings, we call out community suggestions for future federated learning works.