About Me

Both nature and human society are made up of a variety of networks, and AI gives us new capabilities to understand and control these complex systems. I'm trying to use AI techniques (especially deep learning) to push classic network theories beyond their limitations.

I'm currently working on network reconstructing, which means inferring the underlying structure and dynamics from observed data.

I have knowledge from different fields (computer algorithms, programming skills, complex systems, sociology and business operations experience, etc.) to help advance my exploration.



A General Deep Learning Framework for Network Reconstruction and Dynamics Learning
Zhang Zhang, Yi Zhao, Jing Liu, Shuo Wang, Ruyue Xin and Jiang Zhang*

In this work, we introduce Gumbel Graph Network (GGN), a model-free, data-driven deep learning framework to accomplish network reconstruction and dynamics simulation. Our method can reconstruct many kind of dynamics such as continuous, discrete, and even binary.

This paper was published in 《Applied Network Science》


Neural Gene Network Constructor: A Neural Based Model for Reconstructing Gene Regulatory Network
Zhang Zhang†, Lifei Wang†, Shuo Wang, Ruyi Tao, Jingshu Xiao, Muyun Mou, Jun Cai*, Jiang Zhang*

Here, we present a deep learning model “Neural Gene Network Constructor” (NGNC), for inferring gene regulatory network and reconstructing the gene dynamics simultaneously from time series gene expression data.

download in biorxiv


The Cinderella Complex: Word embeddings reveal gender stereotypes in movies and books
Huimin Xu, Zhang Zhang, Lingfei Wu , Cheng-Jun Wang*

Using the word embedding techniques, we reveal the constructed emotional dependency of female characters on male characters in stories. We call this narrative structure “Cinderella complex”, which assumes that women depend on men in the pursuit of a happy, fulfilling life. We demonstrate the social endorsement of gender stereotypes by showing that gender-stereotypical movies are voted more frequently and rated higher.

This paper was published in 《Plos ONE》


Inference for Network Structure and Dynamics from Time Series Data via Graph Neural Network
Mengyuan Chen, Jiang Zhang*, Zhang Zhang Lun Du, Qiao Hu, Shuo Wang, Jiaqi Zhu

In this paper, we push forward the GGN framework for the network completion problem, GGN adds a new module called the States Learner to infer missing parts of the network. Our framework may have wide application areas where the network structure is hard to obtained and the time series data is rich.

download in arxiv

Art Project: SINKING

I conduct an art project named SINKING.INK with my girl (@ TRY). In this project, we will deepen our understanding of art, science and beauty by creating paintings.

Experience and Skills

Here is a list of some of my skills and projects.

Conduct ML projects with python

Python is the main tool language for my AI research now.
I also like to use python for things like spider coding, data statistics, ​etc.

Web Programming

I used to work in the largest mailbox project (163 mailbox) in China​ as a web engineer.
Later I took charge of the entire web front end engineering at a start up.

Information Security

I majored in information security as an undergraduate at HDU.
I conducted network attacks and traffic analysis on penetration projects.

Teamwork and Management

I am good at leading teams and have led 70 student clubs for school jobs.
I once led a Web front-end engineering​ team at a start-up.

Curriculum Vitae