Zhiqian Chen

Assistant Professor

Computer Sceience and Engineering, Mississippi State University

I am an Assistant Professor in the Computer Science and Engineering Department of Mississippi State University. Before joining MS State in 2020, I have been working as a research assistant at Virginia Tech. I received an outstanding contribution award from Toyota Research North America in 2016. Currently, I am focusing on graph machine learning and its applications on spatial problems, circuit, molecule, etc.

[Award] 4/2022: Appreciate NSF’s support for my research on flows on graphs!
- CRII: Interpretable Influence Propagating and Blocking on Graphs
[Service] 3/2022: Will serve as reviewer of NeurIPS 22’
[Paper] 12/2021: One paper is accepted by SIAM Data Mining (SDM) 22’
- Graph Wavelet for Impact Forecast of Traffic Accidents, with SIAM Early Career Travel Award
[Service] 12/2021: Will serve as reviewer of SIGIR 22’, ICML 22’, IJCAI 22’, KDD 22’
[Paper] 10/2021: Recent works have been selected by AAAI 22’, topics include:
- Graph wavelet, influence maximization, graph learning for hieroglyph, graph dynamics mapping
[Oct. 2021] One work is accepted by IEEE BigData 21’: a hierachical graph learning for traffic impact.
[Paper] 9/2021: One paper about mobility and COVID-19 spreading is accepted by ASONAM 21’.
[Service] 8/2021: Invited to serve as reviewer at AAAI 22’.
[Tutorial] 5/2021: See our tutorial Spreading Model for Epidemics ( GNN, RNN, SIR and PDE) in SDM 21’
[Service] 5/2021: Invited to serve on the program committee as reviwer at NeurlPS 21’, ICML 21’, ICLR 21’.
[Paper] 12/2020: One paper on citation forecast is accepted by AAAI 21’.
[Paper] 10/2020 One paper is accepted by EMNLP 20’.
[Paper & Award] 9/2020 Papers about Kalman filtering and school redistricting are accepted by ACM SIGSPATIAL 20’ with (Best Paper Award)
[Service] 8/2020 I will serve as reviwers in AAAI 21’, SIGIR 20’, SIGKDD 20’, NeurIPS 20’.
[Paper] 3/2020 A survey for Graph Neural Networks (GNN) is online: [preprint]. See more GNN papers here
[Paper] 12/2019: Unsupervised learning for material discovery is published in Nature Communications.
- Selected as 22nd of Top 50 Chemistry and Materials Sciences Articles [Top 50 Collection]

Research Topics

Graph, Network and Flow

Today’s deep learning is still a black box. Similarly, graph neural network is another black box. This incurs difficult in comparison and improvement since each method is acclaimed as state-of-the-art. A unified framework is needed to avoid the potential risks, which is our goal.

Spatial Temporal Mining

Graph neural networks (GNNs) motivate many applications based on network data such as transportation road. However, as a practical scenario, the road has very different characteristics from a smooth network (e.g., social network) often used by GNN experiments. We plan to identify these special features and accordingly adjust GNN to adopt transportation problems.

Materials Discovery

[ with Toyota Research, Illinois Tech ]

Material development heavily relies on domain knowledge and professional’s intuitive, which hinders the discovery of new material. We are collaborating with material experts and propose generative models for boosting material discovery.