PAC-Bayesian Analysis for a Two-Step Hierarchical Multiview Learning Approach
Abstract
We study a two-level multiview learning with more than two views under the PAC-Bayesian framework. This approach, sometimes referred as late fusion, consists in learning sequentially multiple view-specific classifiers at the first level, and then combining these view-specific classifiers at the second level. Our main theoretical result is a generalization bound on the risk of the majority vote which exhibits a term of diversity in the predictions of the view-specific classifiers. From this result it comes out that controlling the trade-off between diversity and accuracy is a key element for multiview learning, which complements other results in multiview learning. Finally, we experiment our principle on multiview datasets extracted from the Reuters RCV1/RCV2 collection.
Cite
Text
Goyal et al. "PAC-Bayesian Analysis for a Two-Step Hierarchical Multiview Learning Approach." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017. doi:10.1007/978-3-319-71246-8_13Markdown
[Goyal et al. "PAC-Bayesian Analysis for a Two-Step Hierarchical Multiview Learning Approach." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017.](https://mlanthology.org/ecmlpkdd/2017/goyal2017ecmlpkdd-pacbayesian/) doi:10.1007/978-3-319-71246-8_13BibTeX
@inproceedings{goyal2017ecmlpkdd-pacbayesian,
title = {{PAC-Bayesian Analysis for a Two-Step Hierarchical Multiview Learning Approach}},
author = {Goyal, Anil and Morvant, Emilie and Germain, Pascal and Amini, Massih-Reza},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2017},
pages = {205-221},
doi = {10.1007/978-3-319-71246-8_13},
url = {https://mlanthology.org/ecmlpkdd/2017/goyal2017ecmlpkdd-pacbayesian/}
}