# FedTP: Federated Learning by Transformer Personalization

arXiv: https://arxiv.org/abs/2211.01572 · HTML: https://mlsanity.com/paper/2211.01572/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 56 references that are in the map.
- First posted on arXiv 3 Nov 2022.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints](https://mlsanity.com/paper/1910.01991/) (2019)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://mlsanity.com/paper/1903.02891/) (2019)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [Think Locally, Act Globally: Federated Learning with Local and Global Representations](https://mlsanity.com/paper/2001.01523/) (2020)
- [Three Approaches for Personalization with Applications to Federated Learning](https://mlsanity.com/paper/2002.10619/) (2020)
- [Personalized Cross-Silo Federated Learning on Non-IID Data](https://mlsanity.com/paper/2007.03797/) (2020)
- [Understanding Robustness of Transformers for Image Classification](https://mlsanity.com/paper/2103.14586/) (2021)
- [Personalized Federated Learning using Hypernetworks](https://mlsanity.com/paper/2103.04628/) (2021)
- [Federated Learning of a Mixture of Global and Local Models](https://mlsanity.com/paper/2002.05516/) (2020)
- [Federated Multi-Task Learning under a Mixture of Distributions](https://mlsanity.com/paper/2108.10252/) (2021)
- [Adaptive Gradient-Based Meta-Learning Methods](https://mlsanity.com/paper/1906.02717/) (2019)

## Built on by (most cited first, 30 of 36)

- [Global and Local Prompts Cooperation via Optimal Transport for Federated Learning](https://mlsanity.com/paper/2403.00041/) (2024)
- [Federated Learning for Connected and Automated Vehicles: A Survey of Existing Approaches and Challenges](https://mlsanity.com/paper/2308.10407/) (2023)
- [Harmonizing Generalization and Personalization in Federated Prompt Learning](https://mlsanity.com/paper/2405.09771/) (2024)
- [Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method](https://mlsanity.com/paper/2409.19610/) (2024)
- [PeFLL: Personalized Federated Learning by Learning to Learn](https://mlsanity.com/paper/2306.05515/) (2023)
- [Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning](https://mlsanity.com/paper/2310.18285/) (2023)
- [Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2410.10114/) (2024)
- [Visual Prompt Based Personalized Federated Learning](https://mlsanity.com/paper/2303.08678/) (2023)
- [FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems](https://mlsanity.com/paper/2304.01534/) (2023)
- [Federated Continual Learning: Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2502.07059/) (2025)
- [Towards Multi-modal Transformers in Federated Learning](https://mlsanity.com/paper/2404.12467/) (2024)
- [NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients](https://mlsanity.com/paper/2308.07761/) (2023)
- [Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2312.13923/) (2023)
- [Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation](https://mlsanity.com/paper/2506.12213/) (2025)
- [Prompt-based Personalized Federated Learning for Medical Visual Question Answering](https://mlsanity.com/paper/2402.09677/) (2024)
- [FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification](https://mlsanity.com/paper/2404.15657/) (2024)
- [Save It All: Enabling Full Parameter Tuning for Federated Large Language Models via Cycle Block Gradient Descent](https://mlsanity.com/paper/2406.11187/) (2024)
- [Personalized Quantum Federated Learning for Privacy Image Classification](https://mlsanity.com/paper/2410.02547/) (2024)
- [pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models](https://mlsanity.com/paper/2507.05394/) (2025)
- [Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion](https://mlsanity.com/paper/2506.21144/) (2025)
- [Recent Advances in Transformer and Large Language Models for UAV Applications](https://mlsanity.com/paper/2508.11834/) (2025)
- [Federated Automatic Differentiation](https://mlsanity.com/paper/2301.07806/) (2023)
- [On the Federated Learning Framework for Cooperative Perception](https://mlsanity.com/paper/2404.17147/) (2024)
- [Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalization](https://mlsanity.com/paper/2408.07966/) (2024)
- [FedAli: Personalized Federated Learning Alignment with Prototype Layers for Generalized Mobile Services](https://mlsanity.com/paper/2411.10595/) (2024)
- [Federated Learning for Large Models in Medical Imaging: A Comprehensive Review](https://mlsanity.com/paper/2508.20414/) (2025)
- [Elastic Federated Learning over Open Radio Access Network (O-RAN) for Concurrent Execution of Multiple Distributed Learning Tasks](https://mlsanity.com/paper/2305.02109/) (2023)
- [Energizing Federated Learning via Filter-Aware Attention](https://mlsanity.com/paper/2311.12049/) (2023)
- [A Statistical Analysis of Deep Federated Learning for Intrinsically Low-dimensional Data](https://mlsanity.com/paper/2410.20659/) (2024)
- [Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead](https://mlsanity.com/paper/2502.06349/) (2025)

## Abstract (arXiv)

Federated learning is an emerging learning paradigm where multiple clients collaboratively train a machine learning model in a privacy-preserving manner. Personalized federated learning extends this paradigm to overcome heterogeneity across clients by learning personalized models. Recently, there have been some initial attempts to apply Transformers to federated learning. However, the impacts of federated learning algorithms on self-attention have not yet been studied. This paper investigates this relationship and reveals that federated averaging algorithms actually have a negative impact on self-attention where there is data heterogeneity. These impacts limit the capabilities of the Transformer model in federated learning settings. Based on this, we propose FedTP, a novel Transformer-based federated learning framework that learns personalized self-attention for each client while aggregating the other parameters among the clients. Instead of using a vanilla personalization mechanism that maintains personalized self-attention layers of each client locally, we develop a learn-to-personalize mechanism to further encourage the cooperation among clients and to increase the scablability and generalization of FedTP. Specifically, the learn-to-personalize is realized by learning a hypernetwork on the server that outputs the personalized projection matrices of self-attention layers to generate client-wise queries, keys and values. Furthermore, we present the generalization bound for FedTP with the learn-to-personalize mechanism. Notably, FedTP offers a convenient environment for performing a range of image and language tasks using the same federated network architecture - all of which benefit from Transformer personalization. Extensive experiments verify that FedTP with the learn-to-personalize mechanism yields state-of-the-art performance in non-IID scenarios. Our code is available online.