Contrastive Clustering

Authors

  • Yunfan Li College of Computer Science, Sichuan University, China
  • Peng Hu College of Computer Science, Sichuan University, China
  • Zitao Liu TAL Education Group, China
  • Dezhong Peng College of Computer Science, Sichuan University, China Shenzhen Peng Cheng Laboratory, China College of Computer & Information Science, Southwest University, China
  • Joey Tianyi Zhou Institute of High Performance Computing, A*STAR, Singapore
  • Xi Peng College of Computer Science, Sichuan University, China

DOI:

https://doi.org/10.1609/aaai.v35i10.17037

Keywords:

Clustering, Representation Learning

Abstract

In this paper, we propose an online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. To be specific, for a given dataset, the positive and negative instance pairs are constructed through data augmentations and then projected into a feature space. Therein, the instance- and cluster-level contrastive learning are respectively conducted in the row and column space by maximizing the similarities of positive pairs while minimizing those of negative ones. Our key observation is that the rows of the feature matrix could be regarded as soft labels of instances, and accordingly the columns could be further regarded as cluster representations. By simultaneously optimizing the instance- and cluster-level contrastive loss, the model jointly learns representations and cluster assignments in an end-to-end manner. Besides, the proposed method could timely compute the cluster assignment for each individual, even when the data is presented in streams. Extensive experimental results show that CC remarkably outperforms 17 competitive clustering methods on six challenging image benchmarks. In particular, CC achieves an NMI of 0.705 (0.431) on the CIFAR-10 (CIFAR-100) dataset, which is an up to 19% (39%) performance improvement compared with the best baseline. The code is available at https://github.com/XLearning-SCU/2021-AAAI-CC.

Downloads

Published

2021-05-18

How to Cite

Li, Y., Hu, P., Liu, Z., Peng, D., Zhou, J. T., & Peng, X. (2021). Contrastive Clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 8547-8555. https://doi.org/10.1609/aaai.v35i10.17037

Issue

Section

AAAI Technical Track on Machine Learning III