Zhiqian Chen

Computer Science

Virginia Tech

I will join Computer Science and Engineering Department of Mississippi State University in Fall 2020. Before joining MSU, I have been working as research assistant at Virginia Tech under the supervision of Chang-Tien Lu. My Master Degree is obtained from Peking University and a B.S. from Huazhong University of Science and Technology respectively. I received an outstanding contribution award from Toyota Research North America in 2016. My research focuses on graph mining, spatial data mining, computational art, explainable AI and complex system.

Multiple fully funded Ph.D. and Master positions are available. Details about admission are provided here.

News

A Survey for Graph Neural Networks is online: [preprint]
Discovery for energy material is published in Nature Communications. [Editors’ Highlights]
The work using graph neural network for circuit security is accepted by DATE 2020
Solution for dividing school zones is accepted by ACM SIG-SPATIAL and AAAI 2020

Featured Works

Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks

The success of deep learning has been widely recognized in many machine learning tasks during the last decades, ranging from image …

Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Chang-Tien Lu

PDF

Rational Neural Networks for Approximating Jump Discontinuities of Graph Convolution Operator

A rational neural networks for improving graph node-level embeddings.

Zhiqian Chen, Feng Chen, Rongjie Lai, Xuchao Zhang, Chang-Tien Lu

PDF Code Slides DOI

Learning to Fuse Music Genres with Generative Adversarial Dual Learning

Extend GAN to fuse different domains in an unsupervised fashion, which is not only for music fusion but also any other domain.

Zhiqian Chen, Chih-Wei Wu, Yen-Cheng Lu, Alexander Lerch, Chang-Tien Lu

PDF Slides DOI

Research Topics

Graph Mining

[ with University of Taxes at Dallas, Rensselaer Polytechnic Institute ]

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.

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.

Circuit Security and SAT solving

[ with George Manson University ]

Boolean Satisfiability (SAT) problem is a fundamental problem in computer science and the core of many real-world applications such as hardware and software design. However, its solving or estimating hardness of SAT is NP-hard. We are seeking for a series of a methodology by deep learning to significantly accelerate its solving and estimation.

Computational Art

[ with Georgia Tech ]

Computational creativity is a lively research area that focuses on understanding and facilitating human creativity through the implementation of software programs. With the rapid advances in data driven algorithms such as deep learning, the exploration into computational creativity via machine learning approaches have become increasingly popular. Currently, we have been working in music generation and calligraphy.

Spatial Temporal Mining

[ with Virginia Tech ]

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.