Graph Contrastive Clustering

by   Huasong Zhong, et al.

Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements. However, these methods do not take the category information and clustering objective into consideration, thus the learned representations are not optimal for clustering and the performance might be limited. Towards this issue, we first propose a novel graph contrastive learning framework, which is then applied to the clustering task and we come up with the Graph Constrastive Clustering (GCC) method. Different from basic contrastive clustering that only assumes an image and its augmentation should share similar representation and clustering assignments, we lift the instance-level consistency to the cluster-level consistency with the assumption that samples in one cluster and their augmentations should all be similar. Specifically, on the one hand, the graph Laplacian based contrastive loss is proposed to learn more discriminative and clustering-friendly features. On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments. Both of them incorporate the latent category information to reduce the intra-cluster variance while increasing the inter-cluster variance. Experiments on six commonly used datasets demonstrate the superiority of our proposed approach over the state-of-the-art methods.


page 4

page 8


Deep Robust Clustering by Contrastive Learning

Recently, many unsupervised deep learning methods have been proposed to ...

Deep Image Clustering with Category-Style Representation

Deep clustering which adopts deep neural networks to obtain optimal repr...

You Never Cluster Alone

Recent advances in self-supervised learning with instance-level contrast...

Few-Example Clustering via Contrastive Learning

We propose Few-Example Clustering (FEC), a novel algorithm that performs...

Supporting Clustering with Contrastive Learning

Unsupervised clustering aims at discovering the semantic categories of d...

Prototypical Graph Contrastive Learning

Graph-level representations are critical in various real-world applicati...

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

Unsupervised image representations have significantly reduced the gap wi...