Rate-My-LoRA: Efficient and Adaptive Federated Model Tuning for Cardiac MRI Segmentation

2025-01-06

AI Summary

To address the concurrent challenges of privacy preservation, bandwidth constraints, and statistical heterogeneity in multi-center cardiac MRI segmentation, this paper proposes a LoRA-based fine-tuning framework for federated learning. The method introduces an adaptive LoRA parameter aggregation mechanism weighted by local validation accuracy to dynamically quantify client contributions, and jointly optimizes communication efficiency and model personalization through low-rank adaptation. Experiments on a public multi-center cardiac MR dataset demonstrate that, compared with existing LoRA-based federated approaches, the proposed method reduces communication overhead by 62%, improves cross-center Dice score by 3.7 percentage points, and accelerates local fine-tuning convergence by 2.1×—significantly mitigating performance degradation induced by data heterogeneity and limited communication resources.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Cardiovascular disease (CVD) and cardiac dyssynchrony are major public health problems in the United States. Precise cardiac image segmentation is crucial for extracting quantitative measures that help categorize cardiac dyssynchrony. However, achieving high accuracy often depends on centralizing large datasets from different hospitals, which can be challenging due to privacy concerns. To solve this problem, Federated Learning (FL) is proposed to enable decentralized model training on such data without exchanging sensitive information. However, bandwidth limitations and data heterogeneity remain as significant challenges in conventional FL algorithms. In this paper, we propose a novel efficient and adaptive federate learning method for cardiac segmentation that improves model performance while reducing the bandwidth requirement. Our method leverages the low-rank adaptation (LoRA) to regularize model weight update and reduce communication overhead. We also propose a mymethod{} aggregation technique to address data heterogeneity among clients. This technique adaptively penalizes the aggregated weights from different clients by comparing the validation accuracy in each client, allowing better generalization performance and fast local adaptation. In-client and cross-client evaluations on public cardiac MR datasets demonstrate the superiority of our method over other LoRA-based federate learning approaches.

Problem

• Federated Learning
• Cardiac MRI Segmentation
• Privacy Protection

Innovation

• Rate-My-LoRA
• Federated Learning
• Heart MRI Segmentation