Dissimilarity Mixture Autoencoder for Deep Clustering
arXiv:2006.08177
Abstract
The dissimilarity mixture autoencoder (DMAE) is a neural network model for feature-based clustering that incorporates a flexible dissimilarity function and can be integrated into any kind of deep learning architecture. It internally represents a dissimilarity mixture model (DMM) that extends classical methods like K-Means, Gaussian mixture models, or Bregman clustering to any convex and differentiable dissimilarity function through the reinterpretation of probabilities as neural network representations. DMAE can be integrated with deep learning architectures into end-to-end models, allowing the simultaneous estimation of the clustering and neural network's parameters. Experimental evaluation was performed on image and text clustering benchmark datasets showing that DMAE is competitive in terms of unsupervised classification accuracy and normalized mutual information. The source code with the implementation of DMAE is publicly available at: https://github.com/juselara1/dmae
arXiv comment20 pages (2.5 pages of references)
References in corpus (9)
- Categorical Reparameterization with Gumbel-Softmax
- Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
- Learning Discrete Representations via Information Maximizing Self-Augmented Training
- Clustering with Deep Learning: Taxonomy and New Methods
- SpectralNet: Spectral Clustering using Deep Neural Networks
- Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
- Scalable Kernel K-Means Clustering with Nystrom Approximation: Relative-Error Bounds