Prof. Bin Gu
Nanjing University of Information Science and Technology, China

Bio: Bin Gu currently is an assistant professor of the department of machine learning in Mohamed bin Zayed University of Artificial Intelligence. Before joining MBZUAI, he was a full professor of Nanjing University of Information Science and Technology. His research interests focus on large scaling optimization in machine learning and data mining. He has published 70 more papers, with over 3,000 citations according to Google Scholar.  He served as a program committee member or reviewer for several leading machine learning and data mining conferences and journals such as NeurIPS, ICML, KDD, AAAI, TPAMI, JMLR, and a senior program committee member of IJCAI 2019-2021.
Speech title: Fast and Secure Vertical Federated Learning

Abstract:  In a lot of real-world machine learning applications, data are provided by multiple providers and each maintains private records of different feature sets about common entities. The privacy-preserving federated learning for vertically partitioned data has shown promising results as the solution of the emerging multi-party joint modeling application, in which the data holders collaborate throughout the learning process rather than relying on a trusted third party to hold data. This talk will discuss the challenge of data privacy of vertical federated learning (VFL) compared to the horizontal one. Instead of using traditional secure techniques (such as Encryption, secure multi-party computation, and differential privacy), we utilize the idea of isolating local data and model as much as possible to achieve lightweight and lossless data privacy. We will practice this idea to achieve fast and secure VFLs.