Proceedings Abstracts of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Joint Feature Selection and Structure Preservation for Domain Adaptation / 1697
Jingjing Li, Jidong Zhao, Ke Lu

The essence of domain adaptation is to explore common latent factors shared by the involved domains. These factors can be specific features or geometric structures. Most of previous methods exploit either the shared features or the shared geometric structures separately. However, the two strategies are complementary with each other and jointly exploring them is more optimal. This paper proposes a novel approach, named joint Feature Selection and Structure Preservation (FSSP), for unsupervised domain adaptation. FSSP smoothly integrates structure preservation and feature selection into a unified optimization problem. Intensive experiments on text categorization, image classification and video event recognition demonstrate that our method performs better, even with up to 30% improvement in average, compared with the state-of-the-art methods.