Supporting Clustering with Contrastive Learning

SCCL

4 papers tagged archive 2025-07-28

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

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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.

Paper Source

Papers archive 2025-07-28

4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion
20 May 2023 · 0 repositories · arXiv:2305.12270
Cluster-Level Contrastive Learning for Emotion Recognition in Conversations
7 Feb 2023 · 1 repository · arXiv:2302.03508
Sentiment Analysis of Online Travel Reviews Based on Capsule Network and Sentiment Lexicon
5 Jun 2022 · 0 repositories · arXiv:2206.02160
Supporting Clustering with Contrastive Learning
24 Mar 2021 · 2 repositories · arXiv:2103.12953

Syntology ran 1 of 1 samples · 0 unverified

Tasks archive 2025-07-28

10 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Contrastive Learning	3
Classification	1
Clustering	1
Continual Learning	1
Emotion Recognition	1
Language Modelling	1
Sentiment Analysis	1
Sentiment Classification	1
Short Text Clustering	1
Text Clustering	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (4 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Clustering

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections