Keynote Speeches

Several high-profile speakers will present keynotes at IDEAL, including

  • Xin Yao (University of Birmingham, UK)

    Some Recent Work in Self-aware Computing  


    The first part of the talk will review very briefly what self-awareness means in some psychology and cognitive science literature. Then working definitions of self-awareness and self-expression are given, which are aimed at facilitating the application of such concepts in computing systems. The second part of the talk will present a case study of designing an automated handover algorithm for fully decentralised smart camera networks, which uses the ideas of self-awareness and self-expression. The third and last part of the talk will discuss other related research issues in self-aware and self-expressive computing, and some future research directions.

    More technical details for the second part can be found from the following:

    L. Esterle, P. R. Lewis, B. Rinner and X. Yao, "Socio-Economic Vision Graph Generation and Handover in Distributed Smart Camera Networks," ACM Transactions on Sensor Networks, 10(2), Article No. 20, January 2014.

    P. R. Lewis, L. Esterle, A. Chandra, B. Rinner, J. Torresen and X. Yao, "Static, Dynamic and Adaptive Heterogeneity in Distributed Smart Camera Networks," ACM Transactions on Autonomous and Adaptive Systems (TAAS), 10(2), Article No. 8, 30 pages, June 2015.


    Xin Yao is a Professor of Computer Science in the School of Computer Science at the University of Birmingham and the Director of the Centre of Excellence for Research in Computational Intelligence and Applications (CERCIA). He is also a Fellow of IEEE, a Distinguished Lecturer and a Past (2014-15) President of the IEEE Computational Intelligence Society. He is a Distinguished Visiting Professor at the Nature Inspired Computation and Applications Laboratory (NICAL), USTC-Birmingham Joint Research Institute in Intelligent Computation and Its Applications, University of Science and Technology of China, Hefei, China. His research interests include evolutionary computation (evolutionary optimization, evolutionary learning, evolutionary design), neural network ensembles and multiple classifiers (especially on the diversity issue), meta-heuristic algorithms, data mining, computational complexity of evolutionary algorithms, and various real-world applications. He received a Royal Society Wolfson Research Merit Award in 2012, and the IEEE Computational Intelligence Society Evolutionary Computation Pioneer Award in 2013. `

  • Zhi-Hua Zhou (Nanjing University, China)

    Towards Safe Semi-Supervised Learning  


    In many real tasks there are big data but only a small amount of them are with labels, and it is crucial to exploit unlabeled data to help improve the learning performance. Although there are many successful stories of semi-supervised learning, it has been found that utilizing unlabeled data may hurt the learning performance in many cases. Thus, it is desirable to have safe semi-supervised learning approaches that are able to improve the performance, and never significantly worse than pure supervised learning. In this talk we will give an introduction to some results along this line of research.


    Zhi-Hua Zhou is a Professor, Founding Director of the LAMDA Group, Deputy Director of the National Key Lab for Novel Software Technology at Nanjing University. He authored the books "Ensemble Methods: Foundations and Algorithms" (in English) and “Machine Learning” (in Chinese), and published more than 100 papers in top-tier international journals and conference proceedings. His papers have received more than 22,000 citations, with an h-index of 72. He also holds 16 patents and has good experiences in industrial applications. He has received various awards, including the National Natural Science Award of China, the PAKDD Distinguished Contribution Award, the Microsoft Professorship Award, 12 international journal/conference paper/competition awards, etc. He serves as the Executive Editor-in-Chief of Frontiers of Computer Science, Associate Editor-in-Chief of Science China: Information Sciences, and Associate Editor of ACM TIST, IEEE TNNLS, IEEE TCDS, etc. He founded ACML (Asian Conference on Machine Learning) and served as General Chair and Program Chairs for various conferences including IEEE ICDM'16, IJCAI'15 Machine Learning track, etc. He also serves as Advisory Committee member for IJCAI 2015-2016, and Steering Committee Member of ICDM, PAKDD and PRICAI. He is a Fellow of the AAAI, IEEE, IAPR, IET/IEE, CCF, and an ACM Distinguished Scientist.

  • Longbing Cao (University of Technology Sydney, Australia)

    Data Science and Analytics: Innovation and Practices  


    We are in the era of data science and analytics. While data analytics have been explored from different disciplinary perspectives, most existing analytical and learning systems have been built on assuming that data is independent and identically distributed (IID). Very few people pay attention to the potential issues with the corresponding results, which may be incomplete, misleading or incorrect. A foundational issue in data science and analytics is to understand the non-IID nature of data, business and behavior, while limited knowledge is available in the literature. This talk briefly reviews the issues of existing learning systems, followed by the concepts, fundamentals and examples of non-IIDness learning. The second part of the talk presents a summary of enterprise analytics practices of the speaker’s team, involving diversified domains. Personal thoughts of future data science research directions are provided to conclude the talk.


    Longbing Cao is a professor of information technology at the University of Technology Sydney, Australia. As the founding Director of the university’s research institute: Advanced Analytics Institute, he created a few showcases that have been widely recognized, such as the only group mentioned in Australian government papers on big data and by ATO and OECD reports. Motivated by focusing on both high quality research and high impact development, he proposed several concepts with supporting theories and tools, including non-IIDness learning, behaviour informatics, domain driven data mining, and agent mining. He has been leading large analytical project development for many federal and state government units and large business organizations in Australia and China.

    He has been a key driver of several global initiatives in data science and analytics. He initiated the globally first research degrees in analytics: PhD Analytics and Master of Analytics (Research) in 2011. He is the chair of the IEEE Task Force on Data Science and Advanced Analytics and the IEEE Task Force on Behavioral, Economic, and Socio-cultural Computing, and the chair of the ACM SIGKDD Australia and New Zealand Chapter. He also founded the IEEE International Conference on Data Science and Advanced Analytics, the Editor-in-Chief of the International Journal of Data Science and Analytics, and the Data Analytics book series with Springer. `

  • Bo An (Nanyang Technological University, Singapore)

    Recent Progress on Computational Game Theory for Security 


    Security is a critical concern around the world, whether it’s the challenge of protecting ports, airports and other critical national infrastructure, or protecting wildlife and forests, or suppressing crime in urban areas. In many of these cases, limited security resources prevent full security coverage at all times; instead, these limited resources must be scheduled, avoiding schedule predictability, while simultaneously taking into account different target priorities, the responses of the adversaries to the security posture and potential uncertainty over adversary types. Computational game theory can help design such unpredictable security schedules and new algorithms are now deployed over multiple years in multiple applications for security scheduling. These applications are leading to real-world use-inspired research in computational game theory in scaling up to large-scale problems, handling significant adversarial uncertainty, dealing with bounded rationality of human adversaries, and other interdisciplinary challenges. This talk will discuss some recent research progress on computational game theory for security based on results published at recent AAMAS/AAAI/IJCAI conferences.


    Bo An is a Nanyang Assistant Professor with the School of Computer Engineering, Nanyang Technological University, Singapore. His current research interests include artificial intelligence, multiagent systems, game theory, and optimization. He has published over 40 referred papers at AAMAS, IJCAI, AAAI, ICAPS, JAAMAS and  IEEE Transactions. Dr. An was the recipient of the 2010 IFAAMAS Victor Lesser Distinguished Dissertation Award, an Operational Excellence Award from the Commander, First Coast Guard District of the United States, the Best Innovative Application Paper Award at AAMAS’12, the 2012 INFORMS Daniel H. Wagner Prize for Excellence in Operations Research Practice, and the Innovative Application Award at IAAI-16. He is a member of the Board of Directors of IFAAMAS and the Associate Editor of JAAMAS.