Dr Zhiyuan Luo

Tel: +44 1784 443697
Fax: +44 1784 439786
Email: Zhiyuan.Luo@rhul.ac.uk

I am currently a Professor in the Department of Computer Science and a member of the Computer Learning Research Centre which are both at Royal Holloway, University of London.

Research

My main research interests are in machine learning, data analysis, networked systems and agent-based computing, and applications of these algorithms and techniques.

I am currently involved in the following research projects:

• AstraZeneca: Machine Learning for Chemical Synthesis(1 May 2017 to 30 June 2020) Co-Investigator (with Prof. A. Gammerman (PI) and Prof. V. Vovk)
• EU H2020: ExCAPE Compound Activity Prediction Engine (1 September 2015 to 31 August 2018) Co-Investigator (with Prof. A. Gammerman (PI) and Prof. V. Vovk)
• Engineering and Physical Sciences Research Council (EPSRC) Grant (EP/K033344/1) "Mining the Network Behaviour of Bots" (June 2013 to May 2016) Co-Investigator (with Dr. L. Cavallaro (PI, ISG), Prof. A. Gammerman, Prof. V. Vovk and Dr. H. Shanahan)

Some of past projects:

• Machine learning methods for coal quality analysis based on NIR technology, 2011-2013 (Principal Investigator).
• Royal Society International Joint Project, Explosives Trace Detection with an Odour Capture Hybrid Sensor System, 2009-2011 (Principal Investigator).
• EPSRC EP/E000053/1, Machine Learning for Resource Management in Next-Generation Optical Networks, 2006-2009 (Principal Investigator).
• MRC G0301107, Proteomic Analysis of Human Serum Proteome, 2005-2008 (Principal Co-Investigator).
• EU FP7, Discovery of Novel Serum Biomarkers Based on Aberrant Post-translational Modifications of O-glycoproteins, O-PTM-Biomarkers, and Their Application to Early Detection of Cancer, 2008-2011 (Principal Co-Investigator).
• VLA, Development and Application of Machine Learning Algorithms for the Analysis of Complex Veterinary Data Sets, 2007-2010.

PhD Students

I am always looking to recruit PhD students. I am happy to consider any topic, but for best results, the topic should be in an area close to my current interests (look at my recent publications).

Current PhD students

• Andrej Zukov Gregoric "Towards a question answering view of natural language processing"
• Philip Nadler, jointly with Prof. Mike Spagat (Economics) and Dr. Gregory Chockler (Computer Science)
• Callum Woods, jointly with Dr. Szonya Durant (Psychology) and Dr. Dawn Watling (Psychology)
• Nery Riquelme Granada "Coresets for Conformal Prediction"

Past PhD students

• Mikhail Dashevskiy. "Prediction with performance guarantees", 2006-2009, PhD awarded in 2010 [Research Engineer, DeepMind Google, London, UK].
• Meng Yang, "Feature handling by conformal predictors", 2010-2014, PhD awarded in 2015 [Lecturer, China University of Mining and Technology, China].
• Chenzhe Zhou, "Conformal and Venn predictors for multi-probabilistic Predictions and Their Applications", 2010-2014, PhD awarded in 2015 [Software development engineer, Amazon China].
• Jiaxin Kou, "Faithful Visualisation of Similarities in High Dimensional Data", 2012-2016, PhD awarded in 2016 [Senior developer at Alibaba China].
• Khuong An Nguyen "Machine learning based WiFi location fingerprinting", 2012-2016, PhD awarded in Feb. 2017 [Post-Doc RA at Dept of Computer Science, Royal Holloway, University of London].

Publications

Edited Books

• B. Scholkopf, Z. Luo, V. Vovk (eds), "Empirical Inference - Festschrift in Honor of Vladimir N. Vapnik", ISBN 978-3-642-41135-9, XXVI, 293 p. 61 illus., 39 illus. in colour, Springer, November 2013.
• A. Gammerman, Z. Luo, J. Vega, V. Vovk, "Conformal and Probabilistic Prediction with Applications", ISBN 978-3-319-33394-6, Springer, April 2016.

Edited Proceedings

• A. Gammerman, V. Vovk, Z. Luo and H. Papadopoulos, Proceedings of Machine Learning Research, Volume 60: Conformal and Probabilistic Prediction and Applications, 13-16 June 2017, Stockholm, Sweden
• A. Gammerman, V. Vovk, Z. Luo, E. Smirnov and R. Peeters, Proceedings of Machine Learning Research, Volume 91: Conformal and Probabilistic Prediction and Applications, 11-13 June 2018, Maastricht, The Netherlands.

Best Paper Awards

• H. Wang, X. Liu, I. Nouretdinov and Z. Luo, "A Comparison of Three Implementations of Multi-Label Conformal Predictor", 3rd International Symposium on Statistical Learning and Data Science (SLDS2015), UK, April 20-23, 2015.
• M. Dashevskiy and Z. Luo, "Guaranteed Network Traffic Demand Prediction Using FARIMA Models", 9th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL2008), South Korea, November 2-5, 2008.
• T. Bellotti, Z. Luo and A. Gammerman, "Reliable Classification of Acute Leukaemia from Gene Expression Data using Confidence Machines", IEEE International Conference on Granular Computing, USA, 10-12 May 2006.

Look here for a list of recent publications.

Teaching

I currently teach one undergraduate course and two MSc Big Data courses.

This is a third year course on main ideas of machine learning with a particular emphasis on kernel methods.

• Nearest Neighbours for classification and regression; interesting distances.
• Discriminant analysis.
• Ridge regression and Lasso.
• Support vector machines for classification and regression.
• Kernel trick and its applications to the algorithms covered so far.
• Practically useful kernels, including string kernels.

The MSc core course teaches fundamental facts and skills in data analysis, including machine learning, data mining, and statistics:

• Supervised learning: classification, regression, and ensemble methods.
• Algorithm-independent machine learning.
• Unsupervised learning and clustering. Exploratory data analysis.
• Bayesian methods. Bayes networks and causality.
• Applications, such as information retrieval and natural language processing.

The MSc course (core course for MSc Machine Learning) addresses the on-line framework of machine learning in which the learning system learns and issues predictions or decisions in real time, perhaps in a changing environment. The course teaches protocols, methods and applications of on-line learning.

Information about the courses can be reached from the departmental web page.