Supporting Clustering with Contrastive Learning

Introduced by Zhang et al. in Supporting Clustering with Contrastive Learning

SCCL, or Supporting Clustering with Contrastive Learning, is a framework to leverage contrastive learning to promote better separation in unsupervised clustering. It combines the top-down clustering with the bottom-up instance-wise contrastive learning to achieve better inter-cluster distance and intra-cluster distance. During training, we jointly optimize a clustering loss over the original data instances and an instance-wise contrastive loss over the associated augmented pairs.

Source: Supporting Clustering with Contrastive Learning

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Classification	1	12.50%
Continual Learning	1	12.50%
Emotion Recognition	1	12.50%
Language Modelling	1	12.50%
Sentiment Analysis	1	12.50%
Clustering	1	12.50%
Short Text Clustering	1	12.50%
Text Clustering	1	12.50%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Clustering