Prof. Shuyin Xia

Chongqing University of Posts and Telecommunications, China

Dr. Xia Shuyin is a Professor and Doctoral Supervisor. He serves as the Vice Chairman of the Chongqing Association for Artificial Intelligence and has been recognized as a National-Level Young Talent, Chongqing Outstanding Young Scholar, and Chongqing Talent. He is a Senior Member of IEEE and ranks among the top 2% of the world's top scientists. He holds the positions of Vice Dean of the School of Artificial Intelligence at Chongqing University of Posts and Telecommunications, Director of the Chongqing Key Laboratory of Computational Intelligence, and Deputy Director of the Ministry of Education’s Key Laboratory of Big Data Intelligent Security for Cyberspace. He has led several national key projects, including the National Key R&D Program, NSFC Original Exploration Project, and the National Excellent Young Scientists Fund. Collaborating with Professors Wang Guoyin and Gao Xinbo, he proposed and developed the Granular-Ball Computing Theory. His research outcomes, published as first or corresponding author in top-tier artificial intelligence journals and conferences such as IEEE TPAMI, TKDE, TIP, ICML, AAAI, IJCAI, and ICDE, have attracted follow-up studies by scholars from over 40 world-renowned research institutions. His work has earned awards including the Second Prize of the National Teaching Achievement Award, First Prize of the Chongqing Natural Science Award, First Prize of the CCF Natural Science Award, and the Wu Wenjun Artificial Intelligence Science and Technology Progress Award.

Title: Granular-Ball Computing: An Efficient, Robust, and Interpretable Novel Artificial Intelligence Theory

Abstract:Current artificial intelligence methods predominantly rely on the finest-grained pixel-level or single-granularity representations, lacking the innate efficiency, robustness, and interpretability of human cognitive mechanisms, which prioritize large-scale perception first. To address this, Granular-Ball Computing has been proposed and developed based on multi-granularity cognitive computation theory. This approach mimics the human brain’s "large-scale-first" cognitive process by adopting a coarse-to-fine generation strategy. It uses granular balls of varying sizes to cover data samples, enabling adaptive and efficient multi-granularity representations. By constructing a novel computational paradigm centered on granular balls, it achieves superior efficiency, robustness, and interpretability compared to traditional AI methods. This theory has been tracked and studied by renowned scholars from over 100 research institutions in more than 10 countries/regions worldwide, including the National University of Singapore, the University of Michigan, Seoul National University, the Indian Institute of Technology, and the University of Alberta. This lecture will present key research outcomes and recent advancements in Granular-Ball Computing, including: Granular-Ball Classifier, Granular-Ball Fuzzy Sets, Granular-Ball Clustering, Granular-Ball Graph Learning, Granular-Ball Reinforcement Learning, Granular-Ball Large Models, Granular-Ball Evolutionary Computation, Granular-Ball Rough Sets, Granular-Ball Computer Vision, Granular-Ball Natural Language Processing and so on.