Balanced Self-Paced Learning for Generative Adversarial Clustering Network
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4386-4395
Abstract
Clustering is an important problem in various machine learning applications, but still a challenging task when dealing with complex real data. The existing clustering algorithms utilize either shallow models with insufficient capacity for capturing the non-linear nature of data, or deep models with large number of parameters prone to overfitting. In this paper, we propose a deep Generative Adversarial Clustering Network (ClusterGAN), which tackles the problems of training of deep clustering models in unsupervised manner. \emph{ClusterGAN} consists of three networks, a discriminator, a generator and a clusterer (i.e. a clustering network). We employ an adversarial game between these three players to synthesize realistic samples given discriminative latent variables via the generator, and learn the inverse mapping of the real samples to the discriminative embedding space via the clusterer. Moreover, we utilize a conditional entropy minimization loss to increase/decrease the similarity of intra/inter cluster samples. Since the ground-truth similarities are unknown in clustering task, we propose a novel balanced self-paced learning algorithm to gradually include samples into training from easy to difficult, while considering the diversity of selected samples from all clusters. Therefore, our method makes it possible to efficiently train clusterers with large depth by leveraging the proposed adversarial game and balanced self-paced learning algorithm. According our experiments, ClusterGAN achieves competitive results compared to the state-of-the-art clustering and hashing models on several datasets.Keywords
This publication has 24 references indexed in Scilit:
- Self-Paced Cross-Modal Subspace Matching2016
- Learning A Task-Specific Deep Architecture For Clustering2016
- A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection2015
- Agglomerative clustering via maximum incremental path integralPattern Recognition, 2013
- Image Clustering Using Local Discriminant Models and Global IntegrationIEEE Transactions on Image Processing, 2010
- Survey of Clustering AlgorithmsIEEE Transactions on Neural Networks, 2005
- Assessing a mixture model for clustering with the integrated completed likelihoodIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Normalized cuts and image segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955