Vertical federated learning based on data subset representation for healthcare application.

Journal: Computer methods and programs in biomedicine
PMID:

Abstract

BACKGROUND AND OBJECTIVE: Artificial intelligence is increasingly essential for disease classification and clinical diagnosis tasks in healthcare. Given the strict privacy needs of healthcare data, Vertical Federated Learning (VFL) has been introduced. VFL allows multiple hospitals to collaboratively train models on vertically partitioned data, where each holds only the patient's partial data features, thus maintaining patient confidentiality. However, VFL applications in healthcare scenarios with fewer samples and labels are challenging because existing methods heavily depend on labeled samples and do not consider the intrinsic connections among the data across hospitals.

Authors

  • Yukun Shi
    School of Cyberspace, Hangzhou Dianzi University, Hangzhou, 310018, China.
  • Jilin Zhang
  • Meiting Xue
    School of Cyberspace, Hangzhou Dianzi University, Hangzhou, 310018, China.
  • Yan Zeng
    Department of Urology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • Gangyong Jia
    College of Computer Science, Hangzhou Dianzi University, Hangzhou, China.
  • Qihong Yu
    School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, 310018, China.
  • Miaoqi Li
    School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, 310018, China.