# On the Importance and Applicability of Pre-Training for Federated Learning

arXiv: https://arxiv.org/abs/2206.11488 · HTML: https://mlsanity.com/paper/2206.11488/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- Builds on 77 of its 100 references that are in the map.
- First posted on arXiv 23 Jun 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [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)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)

## Built on by (most cited first, 30 of 71)

- [When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions](https://mlsanity.com/paper/2306.15546/) (2023)
- [Selective Aggregation for Low-Rank Adaptation in Federated Learning](https://mlsanity.com/paper/2410.01463/) (2024)
- [Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation](https://mlsanity.com/paper/2308.15367/) (2023)
- [Integration of Large Language Models and Federated Learning](https://mlsanity.com/paper/2307.08925/) (2023)
- [FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models](https://mlsanity.com/paper/2406.04845/) (2024)
- [Asynchronous Federated Continual Learning](https://mlsanity.com/paper/2304.03626/) (2023)
- [Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting](https://mlsanity.com/paper/2402.15070/) (2024)
- [Federated Large Language Models: Current Progress and Future Directions](https://mlsanity.com/paper/2409.15723/) (2024)
- [FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decomposition](https://mlsanity.com/paper/2404.18848/) (2024)
- [GPT-FL: Generative Pre-trained Model-Assisted Federated Learning](https://mlsanity.com/paper/2306.02210/) (2023)
- [Layer-wise Linear Mode Connectivity](https://mlsanity.com/paper/2307.06966/) (2023)
- [From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcare](https://mlsanity.com/paper/2409.09727/) (2024)
- [FedFisher: Leveraging Fisher Information for One-Shot Federated Learning](https://mlsanity.com/paper/2403.12329/) (2024)
- [animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics](https://mlsanity.com/paper/2406.01253/) (2024)
- [Guiding The Last Layer in Federated Learning with Pre-Trained Models](https://mlsanity.com/paper/2306.03937/) (2023)
- [On the Efficacy of Differentially Private Few-shot Image Classification](https://mlsanity.com/paper/2302.01190/) (2023)
- [Towards Multi-modal Transformers in Federated Learning](https://mlsanity.com/paper/2404.12467/) (2024)
- [Open Challenges and Opportunities in Federated Foundation Models Towards Biomedical Healthcare](https://mlsanity.com/paper/2405.06784/) (2024)
- [Recurrent Early Exits for Federated Learning with Heterogeneous Clients](https://mlsanity.com/paper/2405.14791/) (2024)
- [Federated Online Adaptation for Deep Stereo](https://mlsanity.com/paper/2405.14873/) (2024)
- [Task Arithmetic Through The Lens Of One-Shot Federated Learning](https://mlsanity.com/paper/2411.18607/) (2024)
- [AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models](https://mlsanity.com/paper/2405.16240/) (2024)
- [ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning](https://mlsanity.com/paper/2310.05143/) (2023)
- [Making Batch Normalization Great in Federated Deep Learning](https://mlsanity.com/paper/2303.06530/) (2023)
- [FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning](https://mlsanity.com/paper/2311.13267/) (2023)
- [NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients](https://mlsanity.com/paper/2308.07761/) (2023)
- [Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data](https://mlsanity.com/paper/2311.01420/) (2023)
- [Resilient Contrastive Pre-training under Non-Stationary Drift](https://mlsanity.com/paper/2502.07620/) (2025)
- [Capture Global Feature Statistics for One-Shot Federated Learning](https://mlsanity.com/paper/2503.06962/) (2025)
- [Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning](https://mlsanity.com/paper/2311.08479/) (2023)

## Abstract (arXiv)

Pre-training is prevalent in nowadays deep learning to improve the learned model's performance. However, in the literature on federated learning (FL), neural networks are mostly initialized with random weights. These attract our interest in conducting a systematic study to explore pre-training for FL. Across multiple visual recognition benchmarks, we found that pre-training can not only improve FL, but also close its accuracy gap to the counterpart centralized learning, especially in the challenging cases of non-IID clients' data. To make our findings applicable to situations where pre-trained models are not directly available, we explore pre-training with synthetic data or even with clients' data in a decentralized manner, and found that they can already improve FL notably. Interestingly, many of the techniques we explore are complementary to each other to further boost the performance, and we view this as a critical result toward scaling up deep FL for real-world applications. We conclude our paper with an attempt to understand the effect of pre-training on FL. We found that pre-training enables the learned global models under different clients' data conditions to converge to the same loss basin, and makes global aggregation in FL more stable. Nevertheless, pre-training seems to not alleviate local model drifting, a fundamental problem in FL under non-IID data.