Deep Temporal Contrastive Clustering

12/29/2022
by   Ying Zhong, et al.
0

Recently the deep learning has shown its advantage in representation learning and clustering for time series data. Despite the considerable progress, the existing deep time series clustering approaches mostly seek to train the deep neural network by some instance reconstruction based or cluster distribution based objective, which, however, lack the ability to exploit the sample-wise (or augmentation-wise) contrastive information or even the higher-level (e.g., cluster-level) contrastiveness for learning discriminative and clustering-friendly representations. In light of this, this paper presents a deep temporal contrastive clustering (DTCC) approach, which for the first time, to our knowledge, incorporates the contrastive learning paradigm into the deep time series clustering research. Specifically, with two parallel views generated from the original time series and their augmentations, we utilize two identical auto-encoders to learn the corresponding representations, and in the meantime perform the cluster distribution learning by incorporating a k-means objective. Further, two levels of contrastive learning are simultaneously enforced to capture the instance-level and cluster-level contrastive information, respectively. With the reconstruction loss of the auto-encoder, the cluster distribution loss, and the two levels of contrastive losses jointly optimized, the network architecture is trained in a self-supervised manner and the clustering result can thereby be obtained. Experiments on a variety of time series datasets demonstrate the superiority of our DTCC approach over the state-of-the-art.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/26/2022

Vision Transformer for Contrastive Clustering

Vision Transformer (ViT) has shown its advantages over the convolutional...
research
12/02/2022

MHCCL: Masked Hierarchical Cluster-wise Contrastive Learning for Multivariate Time Series

Learning semantic-rich representations from raw unlabeled time series da...
research
04/22/2023

Unsupervised CD in satellite image time series by contrastive learning and feature tracking

While unsupervised change detection using contrastive learning has been ...
research
10/21/2022

GLCC: A General Framework for Graph-level Clustering

This paper studies the problem of graph-level clustering, which is a nov...
research
11/15/2021

Large-Scale Hyperspectral Image Clustering Using Contrastive Learning

Clustering of hyperspectral images is a fundamental but challenging task...
research
06/01/2022

Strongly Augmented Contrastive Clustering

Deep clustering has attracted increasing attention in recent years due t...
research
01/11/2023

Heterogeneous Tri-stream Clustering Network

Contrastive deep clustering has recently gained significant attention wi...

Please sign up or login with your details

Forgot password? Click here to reset