# Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneity

arXiv: https://arxiv.org/abs/2404.03854 · HTML: https://mlsanity.com/paper/2404.03854/

## Key facts

- Cited by 1 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 37 of its 53 references that are in the map.
- First posted on arXiv 5 Apr 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, 30 of 37)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images](https://mlsanity.com/paper/2003.09871/) (2020)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [Large-Scale Methods for Distributionally Robust Optimization](https://mlsanity.com/paper/2010.05893/) (2020)
- [Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning](https://mlsanity.com/paper/2210.06044/) (2022)
- [Distributionally Robust Federated Averaging](https://mlsanity.com/paper/2102.12660/) (2021)
- [Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training](https://mlsanity.com/paper/2209.07098/) (2022)
- [Graph Optimal Transport for Cross-Domain Alignment](https://mlsanity.com/paper/2006.14744/) (2020)
- [Federated Unsupervised Representation Learning](https://mlsanity.com/paper/2010.08982/) (2020)
- [Robust Federated Learning in a Heterogeneous Environment](https://mlsanity.com/paper/1906.06629/) (2019)
- [Advancing Radiograph Representation Learning with Masked Record Modeling](https://mlsanity.com/paper/2301.13155/) (2023)
- [Divergence-aware Federated Self-Supervised Learning](https://mlsanity.com/paper/2204.04385/) (2022)
- [Collaborative Unsupervised Visual Representation Learning from Decentralized Data](https://mlsanity.com/paper/2108.06492/) (2021)
- [SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger](https://mlsanity.com/paper/2303.17561/) (2023)
- [Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction](https://mlsanity.com/paper/2401.01646/) (2024)
- [FedX: Unsupervised Federated Learning with Cross Knowledge Distillation](https://mlsanity.com/paper/2207.09158/) (2022)
- [Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging](https://mlsanity.com/paper/2205.08576/) (2022)
- [Eliminating Domain Bias for Federated Learning in Representation Space](https://mlsanity.com/paper/2311.14975/) (2023)
- [Learning Aligned Cross-Modal Representations from Weakly Aligned Data](https://mlsanity.com/paper/1607.07295/) (2016)

## Built on by (most cited first, 1 of 1)

- [Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2503.16585/) (2025)

## Abstract (arXiv)

Vision-language pre-training (VLP) has emerged as an effective scheme for multimodal representation learning, but its reliance on large-scale multimodal data poses significant challenges for medical applications. Federated learning (FL) offers a promising solution to scale up the dataset for medical VLP while preserving data privacy. However, we observe that client data heterogeneity in real-world scenarios could cause models to learn biased cross-modal alignment during local pre-training. This would limit the transferability of the federally learned representation model on downstream tasks. To address this challenge, we propose Federated Distributionally Robust Alignment (FedDRA), a framework for federated VLP that achieves robust vision-language alignment under heterogeneous conditions. Based on client datasets, we construct a distribution family that encompasses potential test-time domains, and apply a distributionally robust framework to optimize the pre-trained model's performance across this distribution space. This approach bridges the gap between pre-training samples and downstream applications. To avoid over-fitting on client-specific information, we use anchor representation from the global model to guide the local training, and adopt a two-stage approach to first tune deeper layers before updating the entire network. Extensive experiments on real-world datasets demonstrate FedDRA's effectiveness in enhancing medical federated VLP under data heterogeneity. Our method also adapts well to various medical pre-training methods.