Skip to main navigation
Skip to search
Skip to main content
Illinois Experts Home
LOGIN & Help
Home
Profiles
Research units
Research & Scholarship
Datasets
Honors
Press/Media
Activities
Search by expertise, name or affiliation
Active Heterogeneous Graph Neural Networks with Per-step Meta-Q-Learning
Yuheng Zhang
, Yinglong Xia
, Yan Zhu
, Yuejie Chi
, Lei Ying
,
Hanghang Tong
National Center for Supercomputing Applications (NCSA)
Siebel School of Computing and Data Science
Research output
:
Chapter in Book/Report/Conference proceeding
›
Conference contribution
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Active Heterogeneous Graph Neural Networks with Per-step Meta-Q-Learning'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Q-learning
100%
Heterogeneous Graph Neural Network
100%
Active Learning
75%
Heterogeneous Information Network
75%
Reinforced
50%
Adaptation
25%
Learning Problems
25%
Effective Solutions
25%
Training Data
25%
Superior Performance
25%
Homogeneous Graph
25%
Transfer Learning Algorithm
25%
Active Learning Algorithm
25%
Learning on Graphs
25%
Adaptation Phase
25%
Data Scarcity
25%
Policy Networks
25%
Policy Transfer
25%
Active Learning Framework
25%
Computer Science
Active Learning
100%
Graph Neural Network
100%
Information Network
60%
Training Data
20%
Effective Solution
20%
Learning Algorithm
20%
Learning Problem
20%
Learning Framework
20%
Superior Performance
20%
Neuroscience
Neural Network
100%
Learning Disabilities
25%
Chemical Engineering
Neural Network
100%