ICML 2018oral14 citations

A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks

Akifumi Okuno, Tetsuya Hada, Hidetoshi Shimodaira

Abstract

A simple framework Probabilistic Multi-view Graph Embedding (PMvGE) is proposed for multi-view feature learning with many-to-many associations so that it generalizes various existing multi-view methods. PMvGE is a probabilistic model for predicting new associations via graph embedding of the nodes of data vectors with links of their associations. Multi-view data vectors with many-to-many associations are transformed by neural networks to feature vectors in a shared space, and the probability of new association between two data vectors is modeled by the inner product of their feature vectors. While existing multi-view feature learning techniques can treat only either of many-to-many association or non-linear transformation, PMvGE can treat both simultaneously. By combining Mercer’s theorem and the universal approximation theorem, we prove that PMvGE learns a wide class of similarity measures across views. Our likelihood-based estimator enables efficient computation of non-linear transformations of data vectors in large-scale datasets by minibatch SGD, and numerical experiments illustrate that PMvGE outperforms existing multi-view methods.

BibTeX
@InProceedings{pmlr-v80-okuno18a,
  title = 	 {A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks},
  author =       {Okuno, Akifumi and Hada, Tetsuya and Shimodaira, Hidetoshi},
  booktitle = 	 {Proceedings of the 35th International Conference on Machine Learning},
  pages = 	 {3888--3897},
  year = 	 {2018},
  editor = 	 {Dy, Jennifer and Krause, Andreas},
  volume = 	 {80},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {10--15 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v80/okuno18a/okuno18a.pdf},
  url = 	 {https://proceedings.mlr.press/v80/okuno18a.html},
  abstract = 	 {A simple framework Probabilistic Multi-view Graph Embedding (PMvGE) is proposed for multi-view feature learning with many-to-many associations so that it generalizes various existing multi-view methods. PMvGE is a probabilistic model for predicting new associations via graph embedding of the nodes of data vectors with links of their associations. Multi-view data vectors with many-to-many associations are transformed by neural networks to feature vectors in a shared space, and the probability of new association between two data vectors is modeled by the inner product of their feature vectors. While existing multi-view feature learning techniques can treat only either of many-to-many association or non-linear transformation, PMvGE can treat both simultaneously. By combining Mercer’s theorem and the universal approximation theorem, we prove that PMvGE learns a wide class of similarity measures across views. Our likelihood-based estimator enables efficient computation of non-linear transformations of data vectors in large-scale datasets by minibatch SGD, and numerical experiments illustrate that PMvGE outperforms existing multi-view methods.}
}
A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks · ICML 2018