paper-with-me

Papers

Supporting Clustering with Contrastive Learning

2021-03-24 · NAACL 2021 4 · Dejiao Zhang, Feng Nan, Xiaokai Wei, Shangwen Li, Henghui Zhu, Kathleen McKeown, Ramesh Nallapati, Andrew Arnold, Bing Xiang

Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often overlap with each other in the representation space at the beginning of the learning process, which poses a significant challenge for distance-based clustering in achieving good separation between different categories. To this end, we propose Supporting Clustering with Contrastive Learning (SCCL) -- a novel framework to leverage contrastive learning to promote better separation. We assess the performance of SCCL on short text clustering and show that SCCL significantly advances the state-of-the-art results on most benchmark datasets with 3%-11% improvement on Accuracy and 4%-15% improvement on Normalized Mutual Information. Furthermore, our quantitative analysis demonstrates the effectiveness of SCCL in leveraging the strengths of both bottom-up instance discrimination and top-down clustering to achieve better intra-cluster and inter-cluster distances when evaluated with the ground truth cluster labels.

📄 PDF Abstract BibTeX arXiv:2103.12953

Code (2)

amazon-research/sccl 공식 구현 pytorch
makcedward/nlpaug tf

Tasks

ClusteringContrastive LearningShort Text ClusteringText Clustering

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
SCCL SCCL, or Supporting Clustering with Contrastive Learning, is a framework to leverage contrastive learning to promote better separation in unsupervised clustering. It…

Similar Papers 제목 키워드 기반

Scalable Deep Metric Learning on Attributed Graphs

2024-11-20 · Xiang Li, Gagan Agrawal, Ruoming Jin, Rajiv Ramnath

We consider the problem of constructing embeddings of large attributed graphs and supporting multiple downstream learning tasks. We develop a graph embedding method, which is based on extending deep metric and unbiased c…

Contrastive LearningGraph EmbeddingLink PredictionMetric Learning+2

SegVec3D: A Method for Vector Embedding of 3D Objects Oriented Towards Robot manipulation

2025-07-13 · Zhihan Kang, Boyu Wang arxiv

We propose SegVec3D, a novel framework for 3D point cloud instance segmentation that integrates attention mechanisms, embedding learning, and cross-modal alignment. The approach builds a hierarchical feature extractor to…

Unsupervised Instance SegmentationNatural Language QueriesRobot Manipulation

From Representation to Clusters: A Contrastive Learning Approach for Attributed Hypergraph Clustering

2026-03-10 · Li Ni, Shuaikang Zeng, Lin Mu, Longlong Lin arxiv

Contrastive learning has demonstrated strong performance in attributed hypergraph clustering. Typically, existing methods based on contrastive learning first learn node embeddings and then apply clustering algorithms, su…

Representation LearningContrastive Learning

Joint Debiased Representation and Image Clustering Learning with Self-Supervision

2022-09-14 · Shunjie-Fabian Zheng, JaeEun Nam, Emilio Dorigatti, Bernd Bischl 외

Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing…

ClusteringContrastive LearningImage ClusteringRepresentation Learning

Graph Contrastive Clustering

2021-04-03 · ICCV 2021 10 · Huasong Zhong, Jianlong Wu, Chong Chen, Jianqiang Huang 외

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 infor…

ClusteringContrastive Learning