mlsanityData to 14 Oct 2026

fMBN-E: Efficient Unsupervised Network Structure Ensemble and Selection for Clustering

arXiv 2107.02071 ↗First posted 5 Jul 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

It is known that unsupervised nonlinear dimensionality reduction and clustering is sensitive to the selection of hyperparameters, particularly for deep learning based methods, which hinders its practical use. How to select a proper network structure that may be dramatically different in different applications is a hard issue for deep models, given little prior knowledge of data. In this paper, we aim to automatically determine the optimal network structure of a deep model, named multilayer bootstrap networks (MBN), via simple ensemble learning and selection techniques. Specifically, we first propose an MBN ensemble (MBN-E) algorithm which concatenates the sparse outputs of a set of MBN base models with different network structures into a new representation. Then, we take the new representation produced by MBN-E as a reference for selecting the optimal MBN base models. Moreover, we propose a fast version of MBN-E (fMBN-E), which is not only theoretically even faster than a single standard MBN but also does not increase the estimation error of MBN-E. Importantly, MBN-E and its ensemble selection techniques maintain the simple formulation of MBN that is based on one-nearest-neighbor learning. Empirically, comparing to a number of advanced deep clustering methods and as many as 20 representative unsupervised ensemble learning and selection methods, the proposed methods reach the state-of-the-art performance without manual hyperparameter tuning. fMBN-E is empirically even hundreds of times faster than MBN-E without suffering performance degradation. The applications to image segmentation and graph data mining further demonstrate the advantage of the proposed methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 108 references that are in the map. First posted on arXiv 5 Jul 2021.

Builds on

32 of 108 references.

References · 32

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  3. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  4. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  5. 2015Return of Frustratingly Easy Domain Adaptationcited by 391
  6. 2021Ensemble deep learning: A reviewcited by 284
  7. 2020Contrastive Clusteringcited by 265
  8. 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
  9. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  10. 2019A review of domain adaptation without target labelscited by 156
  11. 2017Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimizationcited by 113
  12. 2017Deep Subspace Clustering Networkscited by 94
20 more
  1. 2019Deep Comprehensive Correlation Mining for Image Clusteringcited by 80
  2. 2020Maximum Density Divergence for Domain Adaptationcited by 76
  3. 2018GEMSEC: Graph Embedding with Self Clusteringcited by 61
  4. 2015Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuitcited by 50
  5. 2018Deep clustering: On the link between discriminative models and K-meanscited by 37
  6. 2017Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoderscited by 32
  7. 2018Deep Multimodal Subspace Clustering Networkscited by 31
  8. 2019N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embeddingcited by 30
  9. 2018Deep Density-based Image Clusteringcited by 28
  10. 2016Locally Weighted Ensemble Clusteringcited by 19
  11. 2013Successive Nonnegative Projection Algorithm for Robust Nonnegative Blind Source Separationcited by 18
  12. 2017Toward Multidiversified Ensemble Clustering of High-Dimensional Data: From Subspaces to Metrics and Beyondcited by 18
  13. 2018Enhanced Ensemble Clustering via Fast Propagation of Cluster-wise Similaritiescited by 17
  14. 2017CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Datacited by 16
  15. 2020Doubly Stochastic Subspace Clusteringcited by 14
  16. 2021Doubly Contrastive Deep Clusteringcited by 9
  17. 2019Weighted Clustering Ensemble: A Reviewcited by 8
  18. 2021Deep NMF Topic Modelingcited by 4
  19. 2020Scattering Transform Based Image Clustering using Projection onto Orthogonal Complementcited by 3
  20. 2014Multilayer bootstrap networkscited by 1

Built on by

Not cited yet.