Modular Dimensionality Reduction

Reeve, Henry W. J.; Mu, Tingting; Brown, Gavin

doi:10.1007/978-3-030-10925-7_37

Modular Dimensionality Reduction

Henry W. J. Reeve, Tingting Mu, Gavin Brown

ECML-PKDD 2018 pp. 605-619

doi:10.1007/978-3-030-10925-7_37 /ecmlpkdd/2018/reeve2018ecmlpkdd-modular/

Abstract

We introduce an approach to modular dimensionality reduction, allowing efficient learning of multiple complementary representations of the same object. Modules are trained by optimising an unsupervised cost function which balances two competing goals: Maintaining the inner product structure within the original space, and encouraging structural diversity between complementary representations. We derive an efficient learning algorithm which outperforms gradient based approaches without the need to choose a learning rate. We also demonstrate an intriguing connection with Dropout. Empirical results demonstrate the efficacy of the method for image retrieval and classification.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Reeve et al. "Modular Dimensionality Reduction." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2018. doi:10.1007/978-3-030-10925-7_37

Markdown

[Reeve et al. "Modular Dimensionality Reduction." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2018.](https://mlanthology.org/ecmlpkdd/2018/reeve2018ecmlpkdd-modular/) doi:10.1007/978-3-030-10925-7_37

BibTeX

@inproceedings{reeve2018ecmlpkdd-modular,
  title     = {{Modular Dimensionality Reduction}},
  author    = {Reeve, Henry W. J. and Mu, Tingting and Brown, Gavin},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2018},
  pages     = {605-619},
  doi       = {10.1007/978-3-030-10925-7_37},
  url       = {https://mlanthology.org/ecmlpkdd/2018/reeve2018ecmlpkdd-modular/}
}