报告题目：Federated Survival Analysis via Data Augmentation Using Multi-task VariationalAutoencoder
报告人：王洪（伟德国际学）
报告时间：2023年5月29日10：00-11：00
报告地点：腾讯会议735534293
摘要：Survival models finds vast applications in biomedical studies. However, survival data used to train these models are usually distributed, censored and facing a growing concern for data privacy. In addition to these issues, it is less commonly recognized that survival times are usually skewed. In this study, we attempt to tackle such challenges via a novel federated learning scheme. The proposed scheme aims to mitigate the censoring and tailed data problems via data augmentation using multi-task variationalautoencoder(MVAE). Experimental results from extensive simulated and real world survival datasets have demonstrated the effectiveness of the proposed methodology with possible deployments at the server or the clients.
报告人简介：王洪，现任伟德国际学数学与统计学院副教授、博士生导师。主要从事机器学习和生物统计等方面的研究工作。在Statistics in Medicine、Artificial Intelligence in Medicine 、Knowledge-Based Systems、Reliability Engineering and System Safety等统计和机器学习期刊发表SCI论文30余篇，获软件著作权1项。
