# FedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning

arXiv: https://arxiv.org/abs/2412.14424 · HTML: https://mlsanity.com/paper/2412.14424/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 19 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 21 of 21)

- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)
- [Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs](https://mlsanity.com/paper/2003.00152/) (2020)
- [Multimodal Federated Learning via Contrastive Representation Ensemble](https://mlsanity.com/paper/2302.08888/) (2023)
- [When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions](https://mlsanity.com/paper/2306.15546/) (2023)
- [FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning](https://mlsanity.com/paper/2302.13485/) (2023)
- [Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models](https://mlsanity.com/paper/2305.11414/) (2023)
- [Strong Baselines for Parameter Efficient Few-Shot Fine-tuning](https://mlsanity.com/paper/2304.01917/) (2023)
- [FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers](https://mlsanity.com/paper/2211.08025/) (2022)
- [Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning](https://mlsanity.com/paper/2211.07864/) (2022)
- [Visual Prompt Based Personalized Federated Learning](https://mlsanity.com/paper/2303.08678/) (2023)
- [FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learning](https://mlsanity.com/paper/2404.15182/) (2024)
- [Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural Networks](https://mlsanity.com/paper/2210.06671/) (2022)
- [Examining Modality Incongruity in Multimodal Federated Learning for Medical Vision and Language-based Disease Detection](https://mlsanity.com/paper/2402.05294/) (2024)
- [Feasibility of Federated Learning from Client Databases with Different Brain Diseases and MRI Modalities](https://mlsanity.com/paper/2406.11636/) (2024)
- [Open-Vocabulary Federated Learning with Multimodal Prototyping](https://mlsanity.com/paper/2404.01232/) (2024)
- [F3OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics](https://mlsanity.com/paper/2411.11912/) (2024)

## Built on by (most cited first, 6 of 6)

- [Vision Foundation Models in Medical Image Analysis: Advances and Challenges](https://mlsanity.com/paper/2502.14584/) (2025)
- [A Survey on Foundation Models for Personalized Federated Intelligence](https://mlsanity.com/paper/2505.06907/) (2025)
- [MCAT: Visual Query-Based Localization of Standard Anatomical Clips in Fetal Ultrasound Videos Using Multi-Tier Class-Aware Token Transformer](https://mlsanity.com/paper/2504.06088/) (2025)
- [FedDEAP: Adaptive Dual-Prompt Tuning for Multi-Domain Federated Learning](https://mlsanity.com/paper/2510.18837/) (2025)
- [FedEU: Evidential Uncertainty-Driven Federated Fine-Tuning of Vision Foundation Models for Remote Sensing Image Segmentation](https://mlsanity.com/paper/2603.07468/) (2026)
- [Prototype-guided Bilateral Alignment Multimodal Federated Learning](https://mlsanity.com/paper/2609.38925/) (2026)

## Abstract (arXiv)

Large Vision-Language Models typically require large text and image datasets for effective fine-tuning. However, collecting data from various sites, especially in healthcare, is challenging due to strict privacy regulations. An alternative is to fine-tune these models on end-user devices, such as in medical clinics, without sending data to a server. These local clients typically have limited computing power and small datasets, which are not enough for fully fine-tuning large VLMs on their own. A naive solution to these scenarios is to leverage parameter-efficient fine-tuning (PEFT) strategies and apply federated learning (FL) algorithms to combine the learned adapter weights, thereby respecting the resource limitations and data privacy. However, this approach does not fully leverage the knowledge from multiple adapters trained on diverse data distributions and for diverse tasks. The adapters are adversely impacted by data heterogeneity and task heterogeneity across clients resulting in suboptimal convergence. To this end, we propose a novel framework called FedPIA that improves upon the naive combinations of FL and PEFT by introducing Permutation and Integration of the local Adapters in the server and global Adapters in the clients exploiting Wasserstein barycenters for improved blending of client-specific and client-agnostic knowledge. This layerwise permutation helps to bridge the gap in the parameter space of local and global adapters before integration. We conduct over 2000 client-level experiments utilizing 48 medical image datasets across five different medical vision-language FL task settings encompassing visual question answering as well as image and report-based multi-label disease detection. Our experiments involving diverse client settings, ten different modalities, and two VLM backbones demonstrate that FedPIA consistently outperforms the state-of-the-art PEFT-FL baselines.