Human-centered Explainable AI

Date Presented: February 18, 2022
Speakers: Professor Yongfeng Zhang

Abstract:
AI has been an important part in many human-centered tasks such as search, recommendation, dialog systems and social networks. However, how to understand and interpret the results produced by AI remains a significant challenge, which greatly influences the trust between humans and AI. In this talk, we will introduce Explainable AI from both technical and application perspectives. In particular, we will highlight the role of human-centered intelligent systems such as search, recommendation and dialog systems as the bridge between human and AI, and as the forefront of human-centered explainable AI research. We will also talk about techniques for human-centered explainable AI including neural symbolic reasoning, causal and counterfactual reasoning, knowledge graph reasoning, explainable graph neural networks, generating natural language explanations, and their application in search, recommendation and dialog systems.

Speaker Bio:
Yongfeng Zhang is an Assistant Professor in the Department of Computer Science at Rutgers University and directs the Web Intelligent Systems and Economics (WISE) lab. His research interest is in Machine Learning, Machine Reasoning, Information Retrieval, Recommender Systems, Economics of Data Science, Explainable AI, Fairness in AI, and AI Ethics. In the previous he was a postdoc at UMass Amherst, and did his PhD and BE in Computer Science at Tsinghua University, with a BS in Economics at Peking University. He serves as associate editor for ACM Transactions on Information Systems (TOIS), ACM Transactions on Recommender Systems (TORS), and Frontiers in Big Data. He is a Siebel Scholar of the class 2015 and an NSF career awardee in 2021.