Topological Gradient-based Competitive Learning

Topological learning is a wide research area aiming at uncovering the mutual spatial relationships between the elements of a set. Some of the most common and oldest approaches involve the use of unsupervised competitive neural networks. However, these methods are not based on gradient optimization which has been proven to provide striking results in feature extraction also in unsupervised learning. Unfortunately, by focusing mostly on algorithmic efficiency and accuracy, deep clustering techniques are composed of overly complex feature extractors, while using trivial algorithms in their top layer. The aim of this work is to present a novel comprehensive theory aspiring at bridging competitive learning with gradient-based learning, thus allowing the use of extremely powerful deep neural networks for feature extraction and projection combined with the remarkable flexibility and expressiveness of competitive learning. In this paper we fully demonstrate the theoretical equivalence of two novel gradient-based competitive layers. Preliminary experiments show how the dual approach, trained on the transpose of the input matrix i.e. $X^T$, lead to faster convergence rate and higher training accuracy both in low and high-dimensional scenarios.

[1]  Robin Sibson,et al.  SLINK: An Optimally Efficient Algorithm for the Single-Link Cluster Method , 1973, Comput. J..

[2]  Giovanni Squillero,et al.  Modeling Generalization in Machine Learning: A Methodological and Computational Study , 2020, ArXiv.

[3]  Miguel A. Molina-Cabello,et al.  A New Self-Organizing Neural Gas Model based on Bregman Divergences , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[4]  Ali Farhadi,et al.  Unsupervised Deep Embedding for Clustering Analysis , 2015, ICML.

[5]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

[6]  Geoffrey J. McLachlan,et al.  Mixture models : inference and applications to clustering , 1989 .

[7]  Giansalvo Cirrincione,et al.  Nonstationary topological learning with bridges and convex polytopes: the G-EXIN neural network , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[8]  D. Defays,et al.  An Efficient Algorithm for a Complete Link Method , 1977, Comput. J..

[9]  Geoffrey E. Hinton,et al.  Autoencoders, Minimum Description Length and Helmholtz Free Energy , 1993, NIPS.

[10]  Martin Krzywinski,et al.  The curse(s) of dimensionality , 2018, Nature Methods.

[11]  Giansalvo Cirrincione,et al.  Discovering Hierarchical Neural Archetype Sets , 2017, IIH-MSP.

[12]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[13]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[14]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[15]  Giovanni Squillero,et al.  Uncovering Coresets for Classification With Multi-Objective Evolutionary Algorithms , 2020, ArXiv.

[16]  J. MacQueen Some methods for classification and analysis of multivariate observations , 1967 .

[17]  Peter J. Rousseeuw,et al.  Finding Groups in Data: An Introduction to Cluster Analysis , 1990 .

[18]  David Zipser,et al.  Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[19]  Dhruv Batra,et al.  Joint Unsupervised Learning of Deep Representations and Image Clusters , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[21]  Bernd Fritzke,et al.  A Self-Organizing Network that Can Follow Non-stationary Distributions , 1997, ICANN.

[22]  Lingfeng Wang,et al.  Deep Adaptive Image Clustering , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[23]  Isabelle Guyon,et al.  Design of experiments for the NIPS 2003 variable selection benchmark , 2003 .

[24]  Karl Pearson F.R.S. LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[25]  Terrence J. Sejnowski,et al.  Unsupervised Learning , 2018, Encyclopedia of GIS.

[26]  Gang Chen,et al.  Deep Learning with Nonparametric Clustering , 2015, ArXiv.

[27]  Ezequiel López-Rubio,et al.  The Growing Hierarchical Neural Gas Self-Organizing Neural Network , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[28]  J. Knott The organization of behavior: A neuropsychological theory , 1951 .

[29]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[30]  R. H. White,et al.  Competitive Hebbian learning , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[31]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[32]  Chia-Wen Lin,et al.  CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data , 2017, IEEE Transactions on Multimedia.

[33]  Giansalvo Cirrincione,et al.  The GH-EXIN neural network for hierarchical clustering , 2020, Neural Networks.

[34]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[35]  Thomas Martinetz,et al.  Topology representing networks , 1994, Neural Networks.

[36]  Masashi Sugiyama,et al.  Learning Discrete Representations via Information Maximizing Self-Augmented Training , 2017, ICML.

[37]  T. Martínez,et al.  Competitive Hebbian Learning Rule Forms Perfectly Topology Preserving Maps , 1993 .