Joint optimization of an autoencoder for clustering and embedding

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Authors

Deep embedded clustering has become a dominating approach to unsupervised categorization of objects with deep neural networks. The optimization of the most popular methods alternates between the training of a deep autoencoder and a k-means clustering of the autoencoder’s embedding. The diachronic setting, however, prevents the former to benefit from valuable information acquired by the latter. In this paper, we present an alternative where the autoencoder and the clustering are learned simultaneously. This is achieved by providing novel theoretical insight, where we show that the objective function of a certain class of Gaussian mixture models (GMM’s) can naturally be rephrased as the loss function of a one-hidden layer autoencoder thus inheriting the built-in clustering capabilities of the GMM. That simple neural network, referred to as the clustering module, can be integrated into a deep autoencoder resulting in a deep clustering model able to jointly learn a clustering and an embedding. Experiments confirm the equivalence between the clustering module and Gaussian mixture models. Further evaluations affirm the empirical relevance of our deep architecture as it outperforms related baselines on several data sets.

OriginalspracheEnglisch
ZeitschriftMachine Learning
Jahrgang110
Ausgabenummer7
Seiten (von - bis)1901-1937
Anzahl der Seiten37
ISSN0885-6125
DOIs
PublikationsstatusErschienen - 01.07.2021

Dokumente

DOI

Zuletzt angesehen

Publikationen

  1. Using Technologies for Foreign Language Learning in Inclusive Settings
  2. Modeling and Performance Analysis of a Node in Fault Tolerant Wireless Sensor Networks
  3. Inverting the Large Lecture Class: Active Learning in an Introductory International Relations Course
  4. A change of values is in the air
  5. Digital Control of a Camless Engine Using Lyapunov Approach with Backward Euler Approximation
  6. Contributions of declarative and procedural memory to accuracy and automatization during second language practice
  7. Multidimensional recurrence quantification analysis (MdRQA) for the analysis of multidimensional time-series
  8. Enhancing Performance of Level System Modeling with Pseudo-Random Signals
  9. Implicit statistical learning and working memory predict EFL development and written task outcomes in adolescents
  10. Dispatching rule selection with Gaussian processes
  11. Scaffolding argumentation in mathematics with CSCL scripts
  12. 7th open challenge on question answering over linked data (QALD-7)
  13. Four Methods to Distinguish between Fractal Dimensions in Time Series through Recurrence Quantification Analysis
  14. A comparison of ML, WLSMV and Bayesian methods for multilevel structural equation models in small samples: A simulation study
  15. A PHENOMENOGRAPHICAL STUDY OF CHILDRENS’ SPATIAL THOUGHT WHILE USING MAPS IN REAL SPACES
  16. Intersection tests for the cointegrating rank in dependent panel data
  17. Challenges and boundaries in implementing social return on investment
  18. Is too much help an obstacle? Effects of interactivity and cognitive style on learning with dynamic versus non-dynamic visualizations with narrative explanations
  19. Volume of Imbalance Container Prediction using Kalman Filter and Long Short-Term Memory
  20. Faulty Process Detection Using Machine Learning Techniques
  21. Investigation and modeling of the material behavior due to evolving dislocation microstructures in fcc and bcc metals
  22. Universal Threshold Calculation for Fingerprinting Decoders using Mixture Models
  23. Explaining and controlling for the psychometric properties of computer-generated figural matrix items
  24. A framework for business model development in technology-driven start-ups
  25. TRY plant trait database – enhanced coverage and open access
  26. Passive Peak Voltage Sensor for Multiple Sending Coils Inductive Power Transmission System
  27. Experiences of the Self between Limit, Transgression, and the Explosion of the Dialectical System
  28. Probabilistic approach to modelling of recession curves
  29. A Hermeneutic Interpretation of Concepts in a Cooperative Multicultural Working Project
  30. Introduction
  31. Are criminals better lie detectors? Investigating offenders' abilities in the context of deception detection
  32. Reciprocal Relationships Between Dispositional Optimism and Work Experiences