Daokun Zhang
Scholar

Daokun Zhang

Google Scholar ID: ar_onRIAAAAJ
University of Nottingham Ningbo China
Graph LearningData MiningMachine Learning
Citations & Impact
All-time
Citations
1,970
 
H-index
15
 
i10-index
20
 
Publications
20
 
Co-authors
4
list available
Resume (English only)
Academic Achievements
  • - Published 27 papers (2016 to 2026)
  • - Scopus Citations: 14
  • - h-index: 14
Research Experience
  • - Assistant Professor, School of Computer Science, University of Nottingham Ningbo China, February 2024 - Present
  • - Research Fellow/Lecturer, Department of Data Science and AI, Monash University, April 2021 - January 2024
  • - Postdoctoral Research Associate, The University of Sydney, June 2019 - April 2021
Education
  • - Ph.D. in Data Science, University of Technology Sydney, August 31, 2015 to November 12, 2019
  • - Supervisor information not provided
Background
  • - Research Interests: Graph machine learning, specifically on graph representation learning, graph structure learning, node classification, and link prediction, etc.
  • - Application Areas: Knowledge graph completion and alignment, combinatorial optimization, computational material and drug discovery, particle system simulation, and geographic data forecasting, etc.
  • - Brief Introduction: Dr. Daokun Zhang has been an Assistant Professor at the School of Computer Science, University of Nottingham Ningbo China since February 2024. Prior to that, he worked as a Research Fellow/Lecturer at the Department of Data Science and AI, Monash University (April 2021 to January 2024), and as a Postdoctoral Research Associate at The University of Sydney (June 2019 to April 2021). He is dedicated to applying graph machine learning techniques to solve real-world problems across different disciplines.
Miscellany
  • - Teaching Courses: Linear and Discrete Optimization, Data Modelling and Analysis
  • - Interested in the following research topics: Weakly supervised learning with sparse/noisy labels, Uncertainty quantification for machine learning predictions, Next-generation Graph Neural Networks beyond feature smoothing
  • - Open to internal and external research collaborations