Project: Kernel Learning For Fusing Uncertain Information From Multiple Heterogeneous Sources 

(ONR N00014-09-1-0663)

 

PI: Anil K. Jain, Department of CSE, Michigan State University

Co-PI: Rong Jin and Pang-Ning Tan, Department of CSE, Michigan State University

 

Abstract:

This project will develop a computational framework and efficient algorithms for combining uncertain information from different sources, both quantitative and qualitative, in a unified framework. In particular, we propose a kernel based framework for information fusion that extracts and combines noisy and uncertain information from multiple heterogeneous sources. The key idea is to represent data observations and side information of different types and in different formats uniformly by a kernel matrix. The framework consists of two major components: (1) Kernel learning. Learn a kernel data representation from noisy observation and uncertain side information. This component explicitly addresses the challenge in computing kernel matrices given the noisy observations and uncertainties in side information. (2) Multiple kernel combination. Find the optimal combination of kernels via a maximum margin framework. This component explicitly addresses the challenges in combining multiple kernel matrices in a nonlinear fashion and constructing an effective and reliable decision function given the noisy kernel data representations and uncertain side information.The proposed framework will be applied to a real-world application, namely, information fusion for dynamic social network analysis.
 

Students

  1. Tianbao Yang
  2. Mehrdad Mahdavi

Conference:

  1. S. C. H. Hoi, R. Jin, P. Zhao, and T. Yang, Online Multiple Kernel Classification, Machine Learning 90(2): 289-316, 2013
  2. T. Yang, M. Mahdavi, R. Jin, and S. Zhu, Online Optimization with Gradual Variations, Conference on Learning Theory (COLT), 2012 (Best student paper award)
  3. T. Yang, R. Jin, and M. Mahdavi, Online Kernel Selection: Algorithms and Evaluations, AAAI Conference on Artificial Intelligence (AAAI), 2012
  4. L. Zhang, R. Jin, J. Bu, C. Chen, and X. He, Efficient Online Learning for Large-scale Sparse Kernel Logistic Regression, AAAI Conference on Artificial Intelligence (AAAI), 2012
  5. T. Yang, M. Mahdavi, R. Jin, L. Zhang, and Y. Zhou, Multiple Kernel Learning from Noisy Labels by Stochastic Programming, International Conference on Machine Learning (ICML), 2012
  6. S. Hoi and R. Jin, Fast Bounded Online Gradient Descent Algorithms for Scalable Kernel-Based Online Learning, International Conference on Machine Learning (ICML), 2012
  7. S. S. Bucak, R. Jin, and A. K. Jain, Multi-label Learning with Incomplete Class Assignments, IEEE Conference on Computer Vision and Pattern Recognition (ICCV) 2011
  8. H. Valizadegan, R. Jin, and S. Wang, Learning to Trade Off Between Exploration and Exploitation in Multiclass Bandit Prediction, ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2011
  9. P. Zhao, S. Hoi, and R. Jin, Online AUC Maximization, International Conference on Machine Learning (ICML), 2011
  10. R. Jin, S. Hoi, and T. Yang, Online Kernel Learning, Algorithmic Learning Theory (ALT), 2010
  11. T. Yang, R. Jin, and A. K. Jain, Learning from Noisy Side Information by Generalized Maximum Entropy Model, International Conference on Machine Learning, 2010
  12. T. Yang, R. Jin, A. K. Jain, Y. Zhou, and W. Tong, Unsupervised Transfer Classification: Application to Text Categorization, ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2010