Skip to main navigation
Skip to search
Skip to main content
Illinois Experts Home
LOGIN & Help
Link opens in a new tab
Search content at Illinois Experts
Home
Profiles
Research units
Research & Scholarship
Datasets
Honors
Press/Media
Activities
Heterogeneous Contrastive Learning for Foundation Models and Beyond
Lecheng Zheng
, Baoyu Jing
, Zihao Li
,
Hanghang Tong
,
Jingrui He
Siebel School of Computing and Data Science
National Center for Supercomputing Applications (NCSA)
School of Information Sciences
Informatics
Research output
:
Chapter in Book/Report/Conference proceeding
›
Conference contribution
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Heterogeneous Contrastive Learning for Foundation Models and Beyond'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Foundation Models
100%
Contrastive Learning
100%
Supervised Contrastive Learning
25%
Learning Methods
12%
Multiple Domains
12%
Computer Vision
12%
Explosives
12%
Heterogeneous Data
12%
Emergent Paradigm
12%
Natural Language Processing
12%
Artificial Intelligence
12%
Label Information
12%
Big Data Era
12%
Generalization Ability
12%
Task Heterogeneity
12%
Downstream Task
12%
Big Data Intelligence
12%
Pre-training Tasks
12%
Current Landscape
12%
Learning-based Method
12%
Model Benefit
12%
High-quality Representation
12%
Contrastive Learning Loss
12%
Psychology
Artificial Intelligence
100%
Big Data
100%
Computer Vision
100%
Natural Language Processing
100%
Social Sciences
Contrastive Learning
100%
Self-Supervised Learning
22%
Learning Method
11%
Natural Language Processing
11%
Artificial Intelligence
11%
Big Data
11%
Computer Vision
11%
Neuroscience
Contrastive Learning
100%
Self-Supervised Learning
22%
Natural Language Processing
11%
Artificial Intelligence
11%
Computer Vision
11%
Biochemistry, Genetics and Molecular Biology
Contrastive Learning
100%
Self-Supervised Learning
22%
Natural Language Processing
11%
Artificial Intelligence
11%