TY - GEN
T1 - A graph-based framework for multi-task multi-view learning
AU - He, Jingrui
AU - Lawrence, Rick
PY - 2011
Y1 - 2011
N2 - Many real-world problems exhibit dual-heterogeneity. A single learning task might have features in multiple views (i.e., feature heterogeneity); multiple learning tasks might be related with each other through one or more shared views (i.e., task heterogeneity). Existing multi-task learning or multi-view learning algorithms only capture one type of heterogeneity. In this paper, we introduce Multi-Task MultiView (M2TV) learning for such complicated learning problems with both feature heterogeneity and task heterogeneity. We propose a graph-based framework (GraM2) to take full advantage of the dual-heterogeneous nature. Our framework has a natural connection to Reproducing Kernel Hilbert Space (RKHS). Furthermore, we propose an iterative algorithm (IteM2) for GraM2 framework, and analyze its optimality, convergence and time complexity. Experimental results on various real data sets demonstrate its effectiveness.
AB - Many real-world problems exhibit dual-heterogeneity. A single learning task might have features in multiple views (i.e., feature heterogeneity); multiple learning tasks might be related with each other through one or more shared views (i.e., task heterogeneity). Existing multi-task learning or multi-view learning algorithms only capture one type of heterogeneity. In this paper, we introduce Multi-Task MultiView (M2TV) learning for such complicated learning problems with both feature heterogeneity and task heterogeneity. We propose a graph-based framework (GraM2) to take full advantage of the dual-heterogeneous nature. Our framework has a natural connection to Reproducing Kernel Hilbert Space (RKHS). Furthermore, we propose an iterative algorithm (IteM2) for GraM2 framework, and analyze its optimality, convergence and time complexity. Experimental results on various real data sets demonstrate its effectiveness.
UR - http://www.scopus.com/inward/record.url?scp=80053436238&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80053436238&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:80053436238
SN - 9781450306195
T3 - Proceedings of the 28th International Conference on Machine Learning, ICML 2011
SP - 25
EP - 32
BT - Proceedings of the 28th International Conference on Machine Learning, ICML 2011
T2 - 28th International Conference on Machine Learning, ICML 2011
Y2 - 28 June 2011 through 2 July 2011
ER -