PuSH - Publikationsserver des Helmholtz Zentrums München

Rezaei, M.* ; Dorigatti, E. ; Rügamer, D.* ; Bischl, B.*

Joint debiased representation learning and imbalanced data clustering.

IEEE Xplore, 55-62 (2022)
DOI
One of the most promising approaches for unsu-pervised learning is combining deep representation learning and deep clustering. Some recent works propose to simultaneously learn representation using deep neural networks and perform clustering by defining a clustering loss on top of embedded features. However, these approaches are sensitive to imbalanced data and out-of-distribution samples. As a consequence, these methods optimize clustering by pushing data close to randomly initialized cluster centers. This is problematic when the number of instances varies largely in different classes or a cluster with few samples has less chance to be assigned a good centroid. To overcome these limitations, we introduce a new unsupervised framework for joint debiased representation learning and image clustering. We simultaneously train two deep learning models, a deep representation network that captures the data distribution, and a deep clustering network that learns embedded features and performs clustering. Specifically, the clustering network and learning representation network both take advantage of our proposed statistics pooling block that represents mean, variance, and cardinality to handle the out-of-distribution samples and class imbalance. Our experiments show that using these repre-sentations, one can considerably improve results on imbalanced image clustering across a variety of image datasets. Moreover, the learned representations generalize well when transferred to the out-of-distribution dataset.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Korrespondenzautor
Schlagwörter Imbalanced Data Clustering ; Unsupervised Debiased Representation Learning
ISSN (print) / ISBN 2375-9232
e-ISSN 2375-9259
Konferenztitel 2022 IEEE International Conference on Data Mining Workshops (ICDMW)
Konferenzort Orlando, FL, USA
Zeitschrift IEEE Xplore
Quellenangaben Band: , Heft: , Seiten: 55-62 Artikelnummer: , Supplement: ,
Verlag IEEE
Verlagsort 10662 Los Vaqueros Circle, Po Box 3014, Los Alamitos, Ca 90720-1264 Usa
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Institute of Computational Biology (ICB)
Förderungen German Federal Ministry of Education and Research (BMBF) Munich Center for Machine Learning (MCML)
Bavarian Ministry of Economic Affairs, Regional Development and Energy through the Center for Analytics - Data - Applications (ADA-Center)
Helmholtz Association under the joint research school "Munich School for Data Science - MUDS"