Federated LoRA Adaptation of BiomedCLIP Across Four International Chest X-Ray Cohorts

• URL: http://arxiv.org/abs/2609.02101v1
• Date: Wed, 02 Sep 2026 04:40:05 GMT
• Title: Federated LoRA Adaptation of BiomedCLIP Across Four International Chest X-Ray Cohorts
• Abstract summary: Federated learning lets institutions train a shared model without exchanging data.<n>Low-Rank Adaptation (LoRA) makes this practical at scale by communicating only compact low-rank updates.
• Score: 3.8298947210288374
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated learning (FL) lets institutions train a shared model without exchanging data, and Low-Rank Adaptation (LoRA) makes this practical at scale by communicating only compact low-rank updates. Biomedical imaging is a compelling setting for this combination: patient data are archived behind privacy regulations, and institutions differ widely in scanners, protocols, and compute. Such heterogeneity raises the question of how federated LoRA updates should be aggregated, increasingly pressing as multimodal vision-language models become central to medical image analysis. We benchmark federated Parameter-efficient fine-tuning (PEFT) of BiomedCLIP for chest radiograph classification across four public cohorts on three continents (USA, Vietnam, Spain). Federated LoRA adaptation improves shared-class AUC on all four cohorts over the unadapted BiomedCLIP backbone (mean 0.687 to 0.802), showing that the gains come from federated adaptation rather than from the pretrained model's zero-shot ability. Relative to isolated single-cohort training, federation improves the weaker cohorts while largely preserving the strongest and approaches a centralized reference (0.812) that pools all data. The singular value decomposition (SVD)-based product-space aggregation introduced by FlexLoRA is essential to this gain (naive factor averaging drops mean AUC by 0.097), whereas a drift-correcting optimizer (FedProx) shows no benefit over FedAvg in our single-seed runs, consistent with LoRA's low-rank updates already limiting client drift. Biomedical vision-language models can thus be adapted collaboratively across heterogeneous, geographically distributed institutions without centralizing data.

Related papers

• Federated Multi-Task Learning for Bladder Tumor Segmentation and MIBC Classification Using a Hybrid CNN-Transformer Architecture [0.0]
  We propose a federated multi-task learning framework for joint bladder tumor segmentation and MIBC/NMIBC classification across four clinical centers.<n>The proposed Swin Hybrid model combines a ResNet-34 branch for local texture and boundary information with a Swin-Tiny Transformer for global anatomi- cal context.
  arXiv  Detail & Related papers  (2026-08-31T08:45:05Z)
• FedPref: Federated Preference Learning for Structured Radiology Report Extraction [69.11739400975445]
  Radiology reports describe findings and locations in free text, but downstream search and analysis require these relations in a fixed schema.<n>We introduce FedPref: frozen public language models propose alternative extractions, local annotations rank them, and sites collaboratively train pooled compact Qwen3-8B adapters.<n>On development data from six simulated hospitals with unequal data volume and disease prevalence, FedPref improves client-mean F1 by 2.49 points and worst-site F1 by 9.10 points compared with training each site in isolation.
  arXiv  Detail & Related papers  (2026-08-17T12:29:42Z)
• FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images [34.592227505836156]
  We propose FedCC, a framework for corpus callosum (CC) localization in fetal US images.<n>The framework integrates a frozen DINOv2 backbone with a lightweight YOLO-based detection head.<n>It substantially reduces both computational and communication overhead, making the framework suitable for low-resource environments.
  arXiv  Detail & Related papers  (2026-06-30T09:02:13Z)
• FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data [1.0303353919699785]
  FederatedRSF implements random survival forests, aggregating locally trained survival trees and redistributing only feature-compatible trees to each site.<n>We evaluate FederatedRSF on the GBSG2 breast cancer cohort distributed with the scikit-survival package.
  arXiv  Detail & Related papers  (2026-05-21T18:32:25Z)
• Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction [1.690444853538344]
  We developed an embedding-based FL pipeline for iron deficiency prediction from routine full blood count data.<n>We deployed it across real institutional environments at Amsterdam University Medical Centre (AUMC) and NHS Blood and Transplant (NHSBT)<n>A frozen domain-specific haematology foundation model, DeepCBC, performs site-local representation extraction.
  arXiv  Detail & Related papers  (2026-05-20T16:31:53Z)
• FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment [55.97027207627]
  Fed PDPO (Federated Personalized Direct Preference Optimization) is a personalized framework for preference alignment of large language models (LLMs)<n>It adopts a parameter-efficient fine-tuning architecture where each client maintains a frozen pretrained LLM backbone augmented with a Low-Rank Adaptation (LoRA) adapter, enabling communication-efficient aggregation.<n>Experiments on multiple preference datasets demonstrate state-of-the-art performance, achieving up to 4.80% average accuracy improvements in federated intra-domain and cross-domain settings.
  arXiv  Detail & Related papers  (2026-03-20T08:24:49Z)
• Med-DualLoRA: Local Adaptation of Foundation Models for 3D Cardiac MRI [1.2782432265370094]
  We propose Med-DualLoRA, a client-aware parameter-efficient fine-tuning framework that disentangles globally shared and local low-rank adaptations (LoRA) through additive decomposition.<n>We evaluate our method on a multi-center state-of-the-art cine 3D CMR FM fine-tuned for disease detection using ACDC and combined M&Ms datasets.
  arXiv  Detail & Related papers  (2026-03-11T16:52:21Z)
• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization [90.08459757321405]
  Federated Adam (FedAdam) algorithms suffer from a threefold increase in uplink communication overhead.<n>We propose a novel sparse FedAdam algorithm called FedAdam-SSM, wherein distributed devices sparsify the updates local model parameters and moment estimates.<n>By minimizing the divergence bound between the model trained by FedAdam-SSM and centralized Adam, we optimize the SSM to mitigate the learning performance degradation caused by sparsification error.
  arXiv  Detail & Related papers  (2024-05-28T07:56:49Z)
• Learning Federated Visual Prompt in Null Space for MRI Reconstruction [83.71117888610547]
  We propose a new algorithm, FedPR, to learn federated visual prompts in the null space of global prompt for MRI reconstruction. FedPR significantly outperforms state-of-the-art FL algorithms with 6% of communication costs when given the limited amount of local training data.
  arXiv  Detail & Related papers  (2023-03-28T17:46:16Z)
• Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training [60.892342868936865]
  Federated learning (FL) is a rapidly growing privacy-preserving collaborative machine learning paradigm. We propose a data heterogeneous-robust FL approach, FedGSP, to address this challenge. We show that FedGSP improves the accuracy by 3.7% on average compared with seven state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-01-31T03:15:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.