Welcome to the homepage of Zenglin Xu
News! We will give a tutorial on Probabilistic Matrix/tensor Block Models at AAAI 2012, see here
Zenglin Xu is currently a postdoctoral researcher in Department of Computer Science in Purdue University, working with Dr. Alan Qi. Before this, he is working with Dr. Matthias Seeger in Max Planck Institute for Informatics and Saarland University for a one-year postdoc. He otained his PhD in the Chinese University of Hong Kong, working with Dr. Irwin King and Dr. Michale Lyu. During the summers of 2007 and 2008, he was a visiting student of Dr. Rong Jin in Michigan State University. His research interests include machine learning and its applications to information retrieval, web search, social computing and bioinformatics. He has published papers in several top conferences and journals, such as NIPS, ICML, IJCAI, AAAI, UAI, CIKM, ICDM, IEEE TNN, etc.
Office: 2142Q, LWSN, Purdue University, West Lafayette, IN 47906
I have a wide interest in fields related to machine Learning, data mining, information retrieval, and bioinformatics.
I have done research on semi-supervised learning and kernel learning. I have interest in how to build efficient and effective semi-supervised learning models, which often involves non-convex optimization problems. I also have strong interest in multiple kernel learning, which involves a convex-concave optimization. I devote myself to design effective and efficient optimization methods to solve these machine learning problems. Furthermore, I also have interest in online learning and learning with a budget.
PC Members (2012): AAAI 2012, AAAI 2012 AIWeb track, CIKM 2012, Web Intelligence 2012, ICPR 2012
PC Members (2011): AAAI 2011 AIWeb track, IJCNN 2011, ICANN 2011
Grant Reviewer: Hong Kong RGC
Journal Reviewers: JMLR, IEEE TKDE, IEEE TNN, Patern Recogintion, ACM TKDD, ACM TIST, NeuroComputing
Recent conference papers:
 K. Huang, R. Jin, Z. Xu and C. Liu (2010), Robust Metric Learning with Smooth Optimization Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence (UAI2010), 2010.
 Xu, Z., Jin, R., Yang, H., King, I. and Lyu, Michael R. (2010). Simple and Efficient Multiple Kernel Learning By Group Lasso. In ICML '10: Proceedings of the 27th Annual International Conference on Machine Learning.
 Yang, H., Xu, Z., King, I. and Lyu, Michael R.(2010). Online Learning for Group Lasso. In ICML '10: Proceedings of the 27th Annual International Conference on Machine Learning.
 Xu, Z., Jin, R., Zhu, S., King, I. and Lyu, M. (2010). Smooth Optimization for Effective Multiple Kernel Learning," in In Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI2010), Atlanta, USA, 2010.
 Xu, Z., Jin, R., Zhu, J., King, I., Lyu, M., and Yang, Z. (2009). Adaptive regularization for transductive support vector machine. In Bengio, Y., Bottou, L., Lafferty, J., and Williams, C., editors, Advances in Neural Information Processing Systems 22 (NIPS), pages 2125–2133.
 Yang, Z., Oja, E., King, I., and Xu, Z. (2009). Heavy-tailed symmetric stochastic neighbor embedding. In Bengio, Y., Bottou, L., Lafferty, J., and Williams, C., editors, Advances in Neural Information Processing Systems 22 (NIPS), pages 2169–2177.
 Xu, Z., Jin, R., Lyu, M. R., and King, I. (2009). Discriminative semi-supervised feature selection via manifold regularization. In IJCAI '09: Proceedings of the 21th International Joint Conference on Artificial Intelligence, pages 1303–1308.
 Xu, Z., Jin, R., Ye, J., Lyu, M. R., and King, I. (2009). Non-monotonic feature selection. In ICML '09: Proceedings of the 26th Annual International Conference on Machine Learning, pages 1145–1152, New York, NY, USA. ACM.
 Xu, Z., Jin, R., King, I., and Lyu, M. (2009). An extended level method for efficient multiple kernel learning. In Koller, D., Schuurmans, D., Bengio, Y., and Bottou, L., editors, Advances in Neural Information Processing Systems 21 (NIPS), pages 1825–1832.
 Huang, K., Xu, Z., King, I., and Lyu, M. R. (2009). Supervised self-taught learning: Actively transferring knowledge from unlabeled data. In IJCNN'09: Proceedings of 22th International Joint Conference on Neural Network.
 Huang, K., Xu, Z., King, I., and Lyu, M. R. (2008). Semi-supervised learning from general unlabeled data. IEEE International Conference on Data Mining, 0:273–282.
 Xu, Z., Jin, R., Huang, K., King, I., and Lyu, M. R. (2008). Semi-supervised text categorization by active search. In CIKM '08: Proceedings of the thirteenth ACM international conference on Information and knowledge management, pages 1517–1518, New York, NY, USA. ACM Press.
 Zhu, J., Hoi, S. C., Xu, Z., and Lyu, M. R. (2008). An effective approach to 3d deformable surface tracking. In ECCV '08: Proceedings of the 10th European Conference on Computer Vision, pages 766–779, Berlin, Heidelberg. Springer-Verlag.
 Xu, Z., Jin, R., Zhu, J., King, I., and Lyu, M. R. (2008). Efficient convex relaxation for transductive support vector machine. In Platt, J., Koller, D., Singer, Y., and Roweis, S., editors, Advances in Neural Information Processing Systems 20, pages 1641–1648. MIT Press, Cambridge, MA.
Recent journal papers and book chapters:
 Xu, Z., King, I., Lyu, M. R. and R. Jin (2010). Semi-supervised Feature Selection based on Manifold Regularization. IEEE Transaction on Neural Networks, Pages 1033-1047.
 Xu, Z., Huang, K., Zhu, J., King, I., and Lyu, M. R. (2009). A novel kernel-based maximum a posteriori classification method. Neural Networks, 22(7):977-987.
 Xu, Z., King, I., and Lyu, M. R. (2007). Feature selection based on minimum error minimax probability machine. International Journal of Pattern Recognition and Artificial Intelligence, 21(8):1–14.
 Huang, K., Xu, Z., King, I., Lyu, M. R., and Zhou, Z. (2007). A novel discriminative naive bayesian network for classification. In Mittal, A. and Kassim, A., editors, Bayesian Network Technologies: Applications and Graphical Models, pages 1–12. IDEA Group Inc., New York.
Xu, Z. and King, I. (2012). Introduction to Semi-supervised Learning (In preparation). Chapman & Hall/CRC.
I have been a tutor of the following courses: