2022 IEEE ICDM Research Contributions Award: Professor Xindong Wu

Professor Wu is Director and Professor of the Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, China. He is a Foreign Member/Academician of the Russian Academy of Engineering, and a Fellow of IEEE and the AAAS (American Association for the Advancement of Science). He won the 2012 IEEE Computer Society Technical Achievement Award "for pioneering contributions to data mining and applications" and the 2014 IEEE ICDM 10-Year Highest Impact Paper Award for a paper on supervised tensor learning.

Professor Wu is a pioneer in Data Mining, and has made major research contributions in big data analytics, data mining with streaming features, and negative association analysis, with original theories and methodologies.

• In January 2014, Wu published a paper titled Data Mining with Big Data (IEEE Transactions on Knowledge and Data Engineering, 2014, 26(1): 97-107), as the first author. This paper presented a HACE theorem that characterizes the (heterogeneous, autonomous, complex, and evolving) features of the Big Data revolution, and proposed a Big Data processing model from the data mining perspective. The HACE theorem has significantly changed the direction of research and development in Data Mining with Big Data, and has opened doors for the data science society to construct new-generation Big Data Analytics systems, which center around domain-specific knowledge and users, rather than the data. This paper has attracted 3551 citations on Google Scholar as of September 16, 2022.
• At ICML-2010, Wu presented a paper on Online Streaming Feature Selection (ICML-2010, 1159-1166) and published a journal version of this conference paper in TPAMI (Xindong Wu et al., IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(2013), 5: 1178-1192), as the first author. These two papers initiated a research topic on feature selection with streaming features, and have resolved an NP-hard candidate-generation-and-selection problem by heuristic pruning designs, with practical applications including impact crater detection. Streaming feature selection has been further studied on trapezoidal data streams, group structure analysis, feature interaction, multi-label learning, and causality-based feature selection.
• Professor Wu, along with his co-authors, has done much of the seminal work on mining negative association rules. They were the first to consider both frequent and infrequent itemsets and develop a scalable method for mining both positive and negative association rules in large databases, and created the research topic of negative association analysis. This work was first published at ICML-2002 and then in TOIS (2004)(Xindong Wu, et al., Efficient Mining of Both Positive and Negative Association Rules, ACM Transactions on Information Systems, 2004, 22(3): 381-405), and has been followed up by many others to discover more types of negative associations and perform more in-depth analysis on transactional databases. The TOIS (2004) paper has attracted 611 citations, and the ICML-2002 paper has attracted an additional 216 citations on Google Scholar.

Professor Wu is a founder of the Data Mining field, with outstanding contributions in advancing its state-of-the-art. In March 1989, he submitted a grant proposal entitled "Automatic Knowledge Acquisition from Relational Data Bases" to the National Natural Science Foundation of China (NNSFC) as the Principal Investigator, and received the NNSFC support for three years (from January 1, 1990 to December 31, 1992), which was likely the first ever national research grant on Data Mining. In July 1993, he completed his Ph.D. research in the Department of Artificial Intelligence at Edinburgh University, with a dissertation entitled Knowledge Acquisition from Data Bases. He sat on the Program Committees of KDD-1995 and 1996 (the first 2 KDD conferences) and served as Program Co-Chair for KDD-2007. He is the founder of ICDM, and has been the core driving force behind the ICDM conference series. Both KDD and ICDM are ranked as A* conferences by the Computing Research and Education Association of Australasia, CORE Inc. At ICDM 2006, Wu organized a panel on Top 10 Algorithms in Data Mining, and published a paper in 2008 (Xindong Wu et al., Knowledge and Information Systems, 14(2008), 1: 1-37) and a book in 2009 (Xindong Wu and Vipin Kumar, Chapman & Hall/CRC Press, 2009), both on the same topic of Top 10 Algorithms in Data Mining. The 2008 paper has attracted 6447 citations, and the 2009 book (in English) was translated into Chinese in 2013 by Tsinghua University Press and has attracted 1115 citations. His top-10 panel has become an important milestone in the Data Mining history.

2022 IEEE ICDM Nomination and Evaluation Committees

• Chengqi Zhang (Chair), University of Technology Sydney, Australia
• Charu Aggarwal, IBM T. J. Watson Research Center, New York, USA
• James Bailey, University of Melbourne, Australia
• Diane Cook, Washington State University, USA
• Peter Flach, University of Bristol, UK
• Joydeep Ghosh, University of Texas at Austin, USA
• Dimitrios Gunopulos, National and Kapodistrian University of Athens, Greece
• Eamonn Keogh, University of California Riverside, USA
• Vipin Kumar, University of Minnesota, USA
• Jian Pei, Simon Fraser University, Canada
• Claudia Plant, University of Vienna, Austria
• Bhavani Thuraisingham, The University of Texas at Dallas, USA
• Takashi Washio, Osaka University, Japan