Semi-supervised Penalized Output Kernel Regression for Link Prediction

Celine Brouard (1) , Florence d'Alché-Buc (1) , Marie Szafranski (1)

1 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes

Link prediction is addressed as an output kernel learning task through semi-supervised Output Kernel Regression. Working in the framework of RKHS theory with vector- valued functions, we establish a new repre- senter theorem devoted to semi-supervised least square regression. We then apply it to get a new model (POKR: Penalized Output Kernel Regression) and show its relevance us- ing numerical experiments on arti cial net- works and two real applications using a very low percentage of labeled data in a transduc- tive setting.

Domains: Machine Learning [cs.LG]

Celine Brouard, Florence d'Alché-Buc, Marie Szafranski. Semi-supervised Penalized Output Kernel Regression for Link Prediction. 28th International Conference on Machine Learning (ICML 2011), Jun 2011, Bellevue, WA, United States. pp.593--600. ⟨hal-00654123⟩