Contrastive and Non-Contrastive Strategies for Federated Self-Supervised Representation Learning and Deep Clustering

Runxuan Miao; Erdem Koyuncu

doi:10.1109/jstsp.2024.3461311

ScienceGate Book Chapters

JOURNAL ARTICLE

Contrastive and Non-Contrastive Strategies for Federated Self-Supervised Representation Learning and Deep Clustering

Runxuan Miao Erdem Koyuncu

Year: 2024 Journal: IEEE Journal of Selected Topics in Signal Processing Vol: 18 (6)Pages: 1070-1084 Publisher: Institute of Electrical and Electronics Engineers

DOI: 10.1109/jstsp.2024.3461311

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Cluster analysis Artificial intelligence Contrastive analysis Feature learning Natural language processing Representation (politics) Deep learning Pattern recognition (psychology) Linguistics

Metrics

Cited By

1.28

FWCI (Field Weighted Citation Impact)

Refs

0.78

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Privacy-Preserving Technologies in Data

Physical Sciences → Computer Science → Artificial Intelligence

Authorship Attribution and Profiling

Physical Sciences → Computer Science → Artificial Intelligence

Contrastive and Non-Contrastive Strategies for Federated Self-Supervised Representation Learning and Deep Clustering

Metrics

Citation History

Topics

Related Documents

Self-Supervised Video Representation Learning Using Improved Instance-Wise Contrastive Learning and Deep Clustering

Deep contrastive representation learning for supervised tasks

Contrasting Contrastive Self-Supervised Representation Learning Pipelines

Contrastive Heartbeats: Contrastive Learning for Self-Supervised ECG Representation and Phenotyping

Contrastive self-representation learning for data clustering