Deep Unsupervised Clustering Using Mixture of Autoencoders
arXiv:1712.07788
Abstract
Unsupervised clustering is one of the most fundamental challenges in machine learning. A popular hypothesis is that data are generated from a union of low-dimensional nonlinear manifolds; thus an approach to clustering is identifying and separating these manifolds. In this paper, we present a novel approach to solve this problem by using a mixture of autoencoders. Our model consists of two parts: 1) a collection of autoencoders where each autoencoder learns the underlying manifold of a group of similar objects, and 2) a mixture assignment neural network, which takes the concatenated latent vectors from the autoencoders as input and infers the distribution over clusters. By jointly optimizing the two parts, we simultaneously assign data to clusters and learn the underlying manifolds of each cluster.
8 pages, 7 figures
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
- Deep Sparse Subspace Clustering
- Riemannian Multi-Manifold Modeling
- Infinite Variational Autoencoder for Semi-Supervised Learning
Cited by in corpus (9)
- MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering
- Unsupervised Learning for Identifying Events in Active Target Experiments
- Supporting Clustering with Contrastive Learning
- Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer
- Segment-Based Credit Scoring Using Latent Clusters in the Variational Autoencoder
- Variational Mixture of Normalizing Flows
- A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm
- You Never Cluster Alone
- From Time Series to Euclidean Spaces: On Spatial Transformations for Temporal Clustering