陈枳扦

陈枳扦 Chen, Zhiqian

Assistant Prof.

Mississippi State Univ.

I am an Assistant Professor of Computer Science and Engineering at Mississippi State University, currently focusing on dynamic behaviors over graphs and networks (see my research interests). For students interested in my research, please explore the opportunities to work with me. If you are interested in my courses, please preview the course syllabi.

🚀 Join us at SIAM Mathematics & Data Science 2024 and CIKM 2024 for our tutorial on Unifying Spectral and Spatial Graph Neural Network.
  • [Grant] 7/24: Received a NSF CNS/CIRC fund (PI) to develop grand theory for graph dynamics.
  • [Grant] 6/24: We will start working on the spatial epidemiology of animal disease with USDA scientists under USDA-ARS funded project.
  • [Tutorial] 6/24: Check our CVPR 24’ tutorial on Unifying Spectral and Spatial Graph Neural Network. See the tutorial website CVPR 24’ Tutorial.
  • [Grant] 4/24: Received a NSF EDU/ITEST fund (Co-PI) to conduct AI education research. See media report.
  • [Honor] 4/24: Received Excellent Reviewer of the IEEE Transactions on Network Science and Engineering Journal.
  • [Grant] 1/24: Received NSF IIS/III REU supp to fund (PI) undergraduate student research.
  • [Paper] 12/23: 2 papers are accepted by AAAI 24’ proposing Graph Bayesian Optimization to conduct information propagation efficiently.
  • [Paper] 12/23: Our theoretical framework for unifying GNN accepted by ACM Computing Survey, see paper, related work and slides.
  • [Grant] 12/23: Received a Seed Grant from the International Institute to develop collaboration with the U. of Auckland in New Zealand.
  • [Grant] 12/23: Launch a working group on Graph AI doing cross-disciplinary study. Thanks to BCoE.
  • [Tool] 8/23: XFlow is released, which targets modeling generalized graph flows
  • [Grant] 8/23: Received support from USDA-ARS funded project (Co-PI) on disease genetics. Special thanks to CVM@MSState. See our storymap.
  • [Paper] 12/22: One paper is accepted by SIAM Data Mining (SDM) 23’: how seeds interact in higher-order perspective
  • [Textbook] 7/22: Our textbook published by Springer Nature provides numerous code examples, Springer Nature, Amazon
  • [Grant] 4/22: Received NSF’s IIS/III fund (PI): CRII: Interpretable Influence Propagating and Blocking on Graphs
More News

Research Topics

on Graph Dynamics
Spectral Graph Theory

Explore dynamic, directed, heterogeneous graph representations.

Higher-order Analysis on Graphs

Develop higher-order analysis methods for graph dynamics.

Graph Uncertainty Quantification

Investigate uncertainty quantification on graph dynamics.

Transdisciplinary Graph Dynamics

How to integrate multidisciplinary advances in graph dynamics.

Graph for Bio-info/medicine

Genetics, Brain, Spatial Epidemiology.

LLM for Graphs

Explore the use of LLM for graph dynamics.

Grants, Awards & Honors

NSF
NSF ITEST
Co-PI - SmartCT: Develop AI education program for K-12 students in Mississippi.
NSF
NSF CIRC
PI - Develop Grand Theory for Graph Dynamics.
NSF
NSF REU - Supplement
Sole-PI: Develop undergraduate research experience on graph dynamics.
See certificate
MSstate
Global Development Grants
PI: Develop international relationship with University of Auckland in New Zealand.
See certificate
MSstate
Graph AI Working Group
PI: Promote research from social science, biomedical, supply chain, and geoscience.
See certificate
USDA
USDA-ARS
Co-PI - Developing Detection and Modeling Tools for the Geospatial and Environmental Epidemiology of Animal Disease.
NSF
NSF IIS
Sole PI - CRII: Interpretable Influence Propagating and Blocking on Graphs.
See certificate
USDA
USDA-ARS
Co-PI - Advancing Agricultural Research through High Performance Computing

Selected

*
Higher-order Relation in Seeds
How remote seeds can implicitly ``interact’’ with each other in the influence maximization problem?
Higher-order Relation in Seeds
An Unified Framework for Graphs
Is there an unfying framework for all types of graphs, including spectral and spatial, also, directed, higher-order, and dynamic graphs?
An Unified Framework for Graphs
Graph Bayesian Optimization
How to conduct Bayesian optimization over graph problems so as to reduce data use?
Graph Bayesian Optimization
Machine Learning for Computer Scientists and Data Analysts: From an Applied Perspective
A textbook for practitioners and students in computer science and data analysis
Machine Learning for Computer Scientists and Data Analysts: From an Applied Perspective
Graph Learning with Kalman Filtering
Use Kalman filtering to handle uncertainty.
Graph Learning with Kalman Filtering
Graph Learning on Circuits
Ues graph neural network to model circuit, and predict its encryption attribute.
Graph Learning on Circuits
Graph Learning on Street Views
Use streetview to predict the crime statistics.
Graph Learning on Street Views

Contact Me

  • zchen@cse.msstate.edu OR chen.zhiqian.work@gmail.com
  • 304 Butler Hall, 665 Perry Street, MS State, MS 39762