# FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning

arXiv: https://arxiv.org/abs/2607.08368 · HTML: https://mlsanity.com/paper/2607.08368/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model](https://mlsanity.com/paper/2208.11625/) (2022)
- [DENSE: Data-Free One-Shot Federated Learning](https://mlsanity.com/paper/2112.12371/) (2021)
- [XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning](https://mlsanity.com/paper/2006.05148/) (2020)
- [Federated Learning for Internet of Things: Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2111.07494/) (2021)
- [Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments](https://mlsanity.com/paper/2208.11311/) (2022)
- [Global and Local Prompts Cooperation via Optimal Transport for Federated Learning](https://mlsanity.com/paper/2403.00041/) (2024)
- [Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting](https://mlsanity.com/paper/2402.15070/) (2024)
- [Parametric Feature Transfer: One-shot Federated Learning with Foundation Models](https://mlsanity.com/paper/2402.01862/) (2024)
- [One-shot Federated Learning via Synthetic Distiller-Distillate Communication](https://mlsanity.com/paper/2412.05186/) (2024)
- [AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models](https://mlsanity.com/paper/2405.16240/) (2024)
- [Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models](https://mlsanity.com/paper/2405.01494/) (2024)
- [Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference](https://mlsanity.com/paper/2410.11650/) (2024)
- [Capture Global Feature Statistics for One-Shot Federated Learning](https://mlsanity.com/paper/2503.06962/) (2025)
- [Federated Learning for Cyber Physical Systems: A Comprehensive Survey](https://mlsanity.com/paper/2505.04873/) (2025)
- [DeepAFL: Deep Analytic Federated Learning](https://mlsanity.com/paper/2603.00579/) (2026)

## Abstract (arXiv)

With the widespread deployment of basic models in edge intelligence, communication bandwidth has become a core bottleneck restricting the scalability of federated learning. Although one-shot federated learning alleviates this problem by minimizing communication rounds, existing iterative fine-tuning or knowledge distillation methods still face challenges such as high server-side computational costs and hyperparameter sensitivity. Analytical federated learning achieves efficient gradientfree aggregation using least-squares closed-form solutions, but in environments with non-independent and identically distributed data, its static feature assumptions fail, leading to feature manifold misalignment and severely impairing model performance. To address this contradiction, this paper proposes the FedOPAL framework. This framework adapts the visual prompts as feature rectifiers, actively correcting the feature distribution of heterogeneous data to a linearly separable space by applying local proximal constraints, thereby satisfying the theoretical assumptions of analytical federated learning. Experimental results show that FedOPAL not only significantly outperforms the original analytical methods on several benchmarks, but also achieves accuracy comparable to state-of-the-art iterative methods while maintaining zero server-side training costs, providing a new engineering paradigm for efficient collaboration of large models on the edge.