Communication Efficient Tensor Factorization for Decentralized Healthcare Networks

• Authors: Jing Ma, Emory University; Qiuchen Zhang, Emory University; Jian Lou, Emory University; Li Xiong, Emory University; Sivasubramanium Bhavani, Emory University; Joyce Ho, Emory University
• Journal Title: 2021 21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2021)
• Volume: Volume 2021-December
• Publisher: IEEE COMPUTER SOC | 2021-01-01, Pages 1216-1221
• Type of Work: Article | Post-print: After Peer Review
• Publisher DOI: http://doi.org/10.1109/ICDM51629.2021.00147
• Subjects: Health Sciences, Public Health
• Keywords: Science & Technology; Technology; Computer Science, Artificial Intelligence; Computer Science, Information Systems; Computer Science; Tensor Factorization; Decentralized Optimization; Federated Learning; Communication efficient; EHRs

Abstract

Tensor factorization has been proved as an efficient unsupervised learning approach for health data analysis, especially for computational phenotyping, where the high-dimensional Electronic Health Records (EHRs) with patients history of medical procedures, medications, diagnosis, lab tests, etc., are converted to meaningful and interpretable medical concepts. Federated tensor factorization distributes the tensor computation to multiple workers under the coordination of a central server, which enables jointly learning the phenotypes across multiple hospitals while preserving the privacy of the patient information. However, existing federated tensor factorization algorithms encounter the single-point-failure issue with the involvement of the central server, which is not only easily exposed to external attacks, but also limits the number of clients sharing information with the server under restricted uplink bandwidth. In this paper, we propose CiderTF, a communication-efficient decentralized generalized tensor factorization, which reduces the uplink communication cost by leveraging a four-level communication reduction strategy designed for a generalized tensor factorization, which has the flexibility of modeling different tensor distribution with multiple kinds of loss functions. Experiments on two real-world EHR datasets demonstrate that CiderTF achieves comparable convergence with the communication reduction up to 99.99%.