AutoEmbedder: A semi-supervised DNN embedding system for clustering
arXiv:2007.05830 · doi:10.1016/j.knosys.2020.106190
Abstract
Clustering is widely used in unsupervised learning method that deals with unlabeled data. Deep clustering has become a popular study area that relates clustering with Deep Neural Network (DNN) architecture. Deep clustering method downsamples high dimensional data, which may also relate clustering loss. Deep clustering is also introduced in semi-supervised learning (SSL). Most SSL methods depend on pairwise constraint information, which is a matrix containing knowledge if data pairs can be in the same cluster or not. This paper introduces a novel embedding system named AutoEmbedder, that downsamples higher dimensional data to clusterable embedding points. To the best of our knowledge, this is the first research endeavor that relates to traditional classifier DNN architecture with a pairwise loss reduction technique. The training process is semi-supervised and uses Siamese network architecture to compute pairwise constraint loss in the feature learning phase. The AutoEmbedder outperforms most of the existing DNN based semi-supervised methods tested on famous datasets.
The manuscript is accepted and published in Knowledge-Based System
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Scikit-learn: Machine Learning in Python
- The NumPy array: a structure for efficient numerical computation
- Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Semi-supervised clustering methods
- Unsupervised Deep Embedding for Clustering Analysis
- SpectralNet: Spectral Clustering using Deep Neural Networks
- Deep Continuous Clustering
- Interpretable Convolutional Neural Networks
- Deep Transductive Semi-supervised Maximum Margin Clustering
- Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders
- A Framework of Transfer Learning in Object Detection for Embedded Systems