Issue No.05 - May (2014 vol.26)
Philip S. Yu , Department of Computer Science, University of Illinois at Chicago, Chicago, IL, USA
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TKDE.2013.111
Domain transfer learning, which learns a target classifier using labeled data from a different distribution, has shown promising value in knowledge discovery yet still been a challenging problem. Most previous works designed adaptive classifiers by exploring two learning strategies independently: distribution adaptation and label propagation. In this paper, we propose a novel transfer learning framework, referred to as Adaptation Regularization based Transfer Learning (ARTL), to model them in a unified way based on the structural risk minimization principle and the regularization theory. Specifically, ARTL learns the adaptive classifier by simultaneously optimizing the structural risk functional, the joint distribution matching between domains, and the manifold consistency underlying marginal distribution. Based on the framework, we propose two novel methods using Regularized Least Squares (RLS) and Support Vector Machines (SVMs), respectively, and use the Representer theorem in reproducing kernel Hilbert space to derive corresponding solutions. Comprehensive experiments verify that ARTL can significantly outperform state-of-the-art learning methods on several public text and image datasets.
textual and multimedia data, Classifier design and evaluation, Design Methodology, Pattern Recognition, Computing Methodologies, Knowledge acquisition, Learning, Artificial Intelligence, Information Technology and Systems, Database Management, Database Applications, Mining methods and algorithms, Modeling structured,
Philip S. Yu, "Adaptation Regularization: A General Framework for Transfer Learning", IEEE Transactions on Knowledge & Data Engineering, vol.26, no. 5, pp. 1, May 2014, doi:10.1109/TKDE.2013.111