用可学习提示提升医疗图像问答模型隐私可靠性
Which Client is Reliable?: A Reliable and Personalized Prompt-based Federated Learning for Medical Image Question Answering
- 在Transformer中引入可学习提示，降低计算成本
- 结合证据理论量化预测不确定性，提升模型可靠性
- 通过最大似然估计平衡准确率与不确定性，适合医疗场景
传统医疗人工智能模型因难以处理敏感医疗数据的隐私问题，限制了其临床应用和引发伦理争议。本文提出一种新型个性化联邦学习（pFL）方法，用于医疗视觉问答（VQA）模型，解决医疗领域中的隐私与可靠性挑战。该方法将可学习提示引入Transformer架构，在不需大量计算资源的情况下高效训练于多样化的医疗数据集。进一步设计了一种可靠的客户端VQA模型，利用Dempster-Shafer证据理论量化预测不确定性，增强模型可信度。此外，提出一种新颖的客户端间通信机制，采用最大似然估计平衡准确率与不确定性，促进跨客户端知识的有效融合。
原文摘要 · Abstract (English)
Conventional medical artificial intelligence (AI) models face barriers in clinical application and ethical issues owing to their inability to handle the privacy-sensitive characteristics of medical data. We present a novel personalized federated learning (pFL) method for medical visual question answering (VQA) models, addressing privacy reliability challenges in the medical domain. Our method introduces learnable prompts into a Transformer architecture to efficiently train it on diverse medical datasets without massive computational costs. Then we introduce a reliable client VQA model that incorporates Dempster-Shafer evidence theory to quantify uncertainty in predictions, enhancing the model's reliability. Furthermore, we propose a novel inter-client communication mechanism that uses maximum likelihood estimation to balance accuracy and uncertainty, fostering efficient integration of insights across clients.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。