Learning to learn empowers an artificial intelligence agent to imitate how human beings continuously and quickly learn a task even with small labeled data. It has achieved notable success in diverse applications, such as image classification, question answering systems, and spatiotemporal prediction. However, typical learning to learn methods overlook the complex structures among the knowledge learned before, which is the crux to achieve fast adaptation in human intelligence.
In this talk, the speaker will introduce their recent efforts on continuously structuring, representing and adapting knowledge in the learning to learn regime. Specifically, he will first discuss several ways to explore and leverage complex and interpretable data-driven structures, which facilitate fast and continual adaptations. He will also present how they involve domain knowledge structures as guidance and deploy it in several real-world E-commerce and smart city applications. Remaining challenges and promising future research directions will also be discussed.
About the Speaker
Huaxiu Yao is currently a Ph.D. candidate of the College of Information Sciences and Technology at the Pennsylvania State University. He obtained his B.Eng. degree from the University of Electronic Science and Technology of China. He also spent time in Amazon A9, Salesforce Research, Alibaba DAMO Academy, Tencent AI Lab and Didi AI Labs. His current research goal is to enable agents to learn quickly and efficiently via knowledge transfer and structure exploration. He is also passionate about applying these methods for solving real-world problems (e.g., smart city, healthcare, E-commerce). His research results have been published in top conferences and journals such as ICML, ICLR, NeurIPS, KDD, AAAI, WWW and WSDM. He has served as a program committee member in major machine learning and data mining conferences.
He is a tenure-track faculty candidate for the Artificial Intelligence & Data Science, Machine Learning & Intelligence cluster.
