arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.03500cs.LGcs.CV
收藏

基于随机排列的视觉Transformer的多任务分布式学习

Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutation

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院)

Sangjoon Park, Jong Chul Ye

摘要:

人工智能在健康研究中的广泛应用目前受到数据可用性的限制。分布式学习方法如联邦学习(FL)和共享学习(SL)被引入来解决这个问题以及数据管理和所有权问题,它们具有不同的优点和缺点。最近提出的联邦分裂任务不可知(FeSTA)学习试图通过视觉Transformer(ViT)架构实现参与者之间的多任务协作来协调FL和SL的独特优点,但它们遭受更高的通信开销。为了解决这个问题,在这里,我们提出了一个多任务的分布式学习使用ViT与随机补丁置换。与FeSTA中使用基于CNN的头部不同,p-FeSTA采用了随机置换的简单补丁嵌入器,在不牺牲隐私的情况下提高了多任务学习性能。实验结果表明,该方法显著提高了多任务协作、通信效率和隐私保护的效果,为医学成像领域的多任务分布式学习提供了新的思路。

英文摘要:

The widespread application of artificial intelligence in health research is currently hampered by limitations in data availability. Distributed learning methods such as federated learning (FL) and shared learning (SL) are introduced to solve this problem as well as data management and ownership issues with their different strengths and weaknesses. The recent proposal of federated split task-agnostic (FeSTA) learning tries to reconcile the distinct merits of FL and SL by enabling the multi-task collaboration between participants through Vision Transformer (ViT) architecture, but they suffer from higher communication overhead. To address this, here we present a multi-task distributed learning using ViT with random patch permutation. Instead of using a CNN based head as in FeSTA, p-FeSTA adopts a randomly permuting simple patch embedder, improving the multi-task learning performance without sacrificing privacy. Experimental results confirm that the proposed method significantly enhances the benefit of multi-task collaboration, communication efficiency, and privacy preservation, shedding light on practical multi-task distributed learning in the field of medical imaging.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑