Jointly Imputing Multi-View Data with Optimal Transport
Yangyang Wu, Xiaoye Miao, Xinyu Huang, Jianwei Yin
Abstract
The multi-view data with incomplete information hinder the effective data analysis. Existing multi-view imputation methods that learn the mapping between complete view and completely missing view are not able to deal with the common multi-view data with missing feature information. In this paper, we propose a generative imputation model named Git with optimal transport theory to jointly impute the missing features/values, conditional on all observed values from the multi-view data. Git consists of two modules, i.e., a multi-view joint generator (MJG) and a masking energy discriminator (MED). The generator MJG incorporates a joint autoencoder with the multiple imputation rule to learn the data distribution from all observed multi-view data. The discriminator MED leverages a new masking energy divergence function to make Git differentiable for imputation enhancement. Extensive experiments on several real-world multi-view data sets demonstrate that, Git yields over 35% accuracy gain, compared to the state-of-the-art approaches.
BibTeX
@article{Wu_Miao_Huang_Yin_2023, title={Jointly Imputing Multi-View Data with Optimal Transport}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25599}, DOI={10.1609/aaai.v37i4.25599}, abstractNote={The multi-view data with incomplete information hinder the effective data analysis. Existing multi-view imputation methods that learn the mapping between complete view and completely missing view are not able to deal with the common multi-view data with missing feature information. In this paper, we propose a generative imputation model named Git with optimal transport theory to jointly impute the missing features/values, conditional on all observed values from the multi-view data. Git consists of two modules, i.e., a multi-view joint generator (MJG) and a masking energy discriminator (MED). The generator MJG incorporates a joint autoencoder with the multiple imputation rule to learn the data distribution from all observed multi-view data. The discriminator MED leverages a new masking energy divergence function to make Git differentiable for imputation enhancement. Extensive experiments on several real-world multi-view data sets demonstrate that, Git yields over 35% accuracy gain, compared to the state-of-the-art approaches.}, number={4}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wu, Yangyang and Miao, Xiaoye and Huang, Xinyu and Yin, Jianwei}, year={2023}, month={Jun.}, pages={4747-4755} }