This is an online seminar. Registration is required.
【Tensor Learning Team】
【Date】2024/September/10(Tue) 14:00-15:00(JST)
*【Speaker】Haonan Huang, The School of Automation, Guangdong University of Technology
Title: Multi-view Learning: Effectiveness and Adversarial Robustness
Abstract:
With the increasing prevalence and significance of multi-view data in various aspects of daily life, effectively utilizing and learning from multi-view data has become a critical challenge. In this talk, I will first explore how to leverage the unique properties of multi-view data to develop effective learning paradigms, sharing our recent efforts to address these challenges. Additionally, I will discuss the reliability of multi-view learning models, including our attempts to test their vulnerabilities through adversarial attacks and our strategies to enhance their robustness against such threats.
