Speaker: Yang Zhou

Date: Feb 23, 11:45am–12:45pm

Abstract: Machine learning (ML), a powerful tool for automatically extracting, managing, inferencing, and transferring knowledge, has been proven to be extremely useful in understanding the intrinsic nature of real-world big data. Despite achieving remarkable performance, ML models, especially deep learning models, suffer from severe trustworthiness and scalability challenges: trustworthiness threats against both data and model (e.g., security, privacy, and fairness), huge size of big data vs. limited computational resources, and high complexity of ML models. There is an immediate and crucial need to bridge the gap between theoretical techniques and system principles to develop the next-generation ML frameworks for better understanding of big data and their underlying processes, with improved effectiveness, trustworthiness, and scalability.

In this talk, I will introduce problems, challenges, and solutions for characterizing and understanding effectiveness, trustworthiness, and scalability concerns of ML models in the real world. I will describe my recent research in Trustworthy Machine Learning, Parallel, Distributed, and Federated Learning, and Natural Language Processing. I will also present my interdisciplinary research in Transportation and Healthcare. I will conclude the talk by sketching interesting future directions for trustworthy and scalable machine learning.

Biographical Sketch: Yang Zhou is an Assistant Professor in the Department of Computer Science and Software Engineering at the Auburn University. Prior to that, he received his Ph.D. degree in the College of Computing at the Georgia Institute of Technology. His current research interests lie in the areas of Trustworthy Machine Learning, Parallel, Distributed, and Federated Learning, Natural Language Processing, Graph Machine Learning, and interdisciplinary research in Transportation and Healthcare. He has published more than 90 research papers in top venues of machine learning (ICML, NeurIPS), artificial intelligence (AAAI, IJCAI, TIST), natural language processing (ACL, EMNLP), high performance computing (HPDC, SC, TPDS), database systems (VLDB, ICDE, TKDE, VLDBJ), data mining (KDD, ICDM, TKDD, DMKD, KAIS), Web (WWW, TWEB), etc. The developed algorithms and systems have been widely used by many research groups and eight papers have been included and taught in courses at universities worldwide. He was named as KDD Rising Star by Microsoft Academic Search in 2016. The lab has built close collaborative relationships with Sony AI, Microsoft Azure AI, and Amazon AWS.

Location and Zoom link: 307 Love, or https://fsu.zoom.us/j/98301205818