EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective

Daniel J. Trosten, Robert Jenssen, Michael C. Kampffmeyer

Proceedings of the Northern Lights Deep Learning Workshop · 2021

DOI: 10.7557/18.5709 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Northern Lights Deep Learning Workshop, 2021. Verfasst von Daniel J. Trosten und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Preservation of local similarity structure is a key challenge in deep clustering. Many recent deep clustering methods therefore use autoencoders to help guide the model's neural network towards an embedding which is more reflective of the input space geometry. However, recent work has shown that autoencoder-based deep clustering models can suffer from objective function mismatch (OFM). In order to improve the preservation of local similarity structure, while simultaneously having a low OFM, we develop a new auxiliary objective function for deep clustering. Our Unsupervised Companion Objective (UCO) encourages a consistent clustering structure at intermediate layers in the network -- helping the network learn an embedding which is more reflective of the similarity structure in the input space. Since a clustering-based auxiliary objective has the same goal as the main clustering objective, it is less prone to introduce objective function mismatch between itself and the main objective. Our experiments show that attaching the UCO to a deep clustering model improves the performance of the model, and exhibits a lower OFM, compared to an analogous autoencoder-based model.

Zitieren

APA

Trosten, D. J., Jenssen, R., & Kampffmeyer, M. C. (2021). Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective. Proceedings of the Northern Lights Deep Learning Workshop. https://doi.org/10.7557/18.5709

Vancouver

Trosten DJ, Jenssen R, Kampffmeyer MC. Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective. Proceedings of the Northern Lights Deep Learning Workshop. 2021. doi:10.7557/18.5709

BibTeX
@article{Trosten2021,
  author = {Trosten, Daniel J. and Jenssen, Robert and Kampffmeyer, Michael C.},
  title = {Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective},
  journal = {Proceedings of the Northern Lights Deep Learning Workshop},
  year = {2021},
  doi = {10.7557/18.5709}
}
Kostenlos starten →