# Guiding The Last Layer in Federated Learning with Pre-Trained Models

arXiv: https://arxiv.org/abs/2306.03937 · HTML: https://mlsanity.com/paper/2306.03937/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 47 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 30 of 35)

- [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)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Local SGD Converges Fast and Communicates Little](https://mlsanity.com/paper/1805.09767/) (2018)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Personalized Federated Learning: A Meta-Learning Approach](https://mlsanity.com/paper/2002.07948/) (2020)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)
- [Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning](https://mlsanity.com/paper/1807.06629/) (2018)
- [Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms](https://mlsanity.com/paper/1808.07576/) (2018)
- [Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning](https://mlsanity.com/paper/2201.03529/) (2022)
- [Probing Representation Forgetting in Supervised and Unsupervised Continual Learning](https://mlsanity.com/paper/2203.13381/) (2022)
- [On the Importance and Applicability of Pre-Training for Federated Learning](https://mlsanity.com/paper/2206.11488/) (2022)
- [Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning](https://mlsanity.com/paper/2210.08090/) (2022)
- [A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning](https://mlsanity.com/paper/2210.04428/) (2022)

## Built on by (most cited first, 13 of 13)

- [Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks](https://mlsanity.com/paper/2312.06795/) (2023)
- [PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning](https://mlsanity.com/paper/2401.02094/) (2024)
- [Accelerating Heterogeneous Federated Learning with Closed-form Classifiers](https://mlsanity.com/paper/2406.01116/) (2024)
- [Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning](https://mlsanity.com/paper/2412.14326/) (2024)
- [FedBaF: Federated Learning Aggregation Biased by a Foundation Model](https://mlsanity.com/paper/2410.18352/) (2024)
- [GC-Fed: Gradient Centralized Federated Learning with Partial Client Participation](https://mlsanity.com/paper/2503.13180/) (2025)
- [Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneity](https://mlsanity.com/paper/2404.03854/) (2024)
- [Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning](https://mlsanity.com/paper/2505.12318/) (2025)
- [Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights](https://mlsanity.com/paper/2509.05142/) (2025)
- [Training-Free Dynamic Upcycling of Expert Language Models](https://mlsanity.com/paper/2603.29765/) (2026)
- [Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server](https://mlsanity.com/paper/2403.14371/) (2024)
- [Site-Level Fine-Tuning with Progressive Layer Freezing: Towards Robust Prediction of Bronchopulmonary Dysplasia from Day-1 Chest Radiographs in Extremely Preterm Infants](https://mlsanity.com/paper/2507.12269/) (2025)
- [How (Mis)calibrated is your Federated CLIP and what to do about it?](https://mlsanity.com/paper/2512.04305/) (2025)

## Abstract (arXiv)

Federated Learning (FL) is an emerging paradigm that allows a model to be trained across a number of participants without sharing data. Recent works have begun to consider the effects of using pre-trained models as an initialization point for existing FL algorithms; however, these approaches ignore the vast body of efficient transfer learning literature from the centralized learning setting. Here we revisit the problem of FL from a pre-trained model considered in prior work and expand it to a set of computer vision transfer learning problems. We first observe that simply fitting a linear classification head can be efficient and effective in many cases. We then show that in the FL setting, fitting a classifier using the Nearest Class Means (NCM) can be done exactly and orders of magnitude more efficiently than existing proposals, while obtaining strong performance. Finally, we demonstrate that using a two-phase approach of obtaining the classifier and then fine-tuning the model can yield rapid convergence and improved generalization in the federated setting. We demonstrate the potential our method has to reduce communication and compute costs while achieving better model performance.