吉林大学王湘浩人工智能杰出学者系列讲座——陈雷教授主题讲座

发布时间:2025-05-06 点击:

 

讲座题目:Effective Data Preprocessing for Deep Learning

报告人:Lei Chen

Chair Professor in Data Science and Analytics at HKUST (GZ)

ACM Fellow  and IEEE Fellow .

讲座时间:2025524日(星期六)下午1630

讲座地点:正新楼3楼智慧教室

Abstract:

Deep learning models, particularly large-scale models, have shown exceptional performance in many applications. However, the success of these models is significantly influenced by the data preprocessing stage. This talk will focus on three key areas of effective data preprocessing for deep learning: 1) Core set selection, which involves identifying a representative subset of data that can capture the underlying patterns of the full dataset, thus reducing training time while maintaining model accuracy;  2) Training optimization, involving computation graph optimization; and 3) Efficient handling of large datasets, addressing techniques like batching, shuffling, and parallel processing to optimize resource usage and training efficiency. Finally, I will discuss emerging trends and research directions in data preprocessing techniques that could enhance the scalability and performance of deep learning models.

Biography:

Lei Chen is a Chair Professor in Data Science and Analytics at HKUST (GZ), a Fellow of ACM and IEEE. Currently, he serves as the Dean of the Information Hub and the Director of the Big Data Institute at HKUST (GZ). Prof. Chen’s research spans several areas, including Data-driven AI, Big Data Analytics, the Metaverse, knowledge graphs, blockchain technology, data privacy, crowdsourcing, and spatial and temporal databases, as well as probabilistic databases. He earned his Ph.D. in Computer Science from the University of Waterloo, Canada.

Prof. Chen has received several prestigious awards, including the SIGMOD Test-of-Time Award in 2015 and the Best Research Paper Award at VLDB 2022. His team’s system also won the Excellent Demonstration Award at VLDB 2014. He served as the Program Committee Co-chair for VLDB 2019 and currently holds the position of Editor-in-Chief for IEEE Transactions on Data and Knowledge Engineering. In addition, he was the General Co-Chair of VLDB 2024 and will serve as the General Co-Chair of IJCAI China 2025.

主办单位:

吉林大学人工智能学院

吉林大学计算机科学与技术学院

吉林大学软件学院

吉林大学数学学院

吉林大学通信工程学院