Yilong Zang

Hello everyone. My name is Yilong Zang (臧屹隆). Welcome to my website.

I am now a remote research assistant at Data Science and its Applications (DSA) Research Group in German Research Center for Artificial Intelligence (DFKI). I am honored to be supervised by Prof. Sebastian Vollmer.

I got my master’s degree from National Engineering Research Center For Multimedia Software at Wuhan University in Sep. 2023. During that time, I was supervised by Prof. Ruimin Hu and Prof. Zheng Wang (co-advisor). My master’s research task is graph-based fraud detection. I mainly analyze the new problems and patterns of fraudsters in graph data, and then design a suitable GNN model to solve the above problems.

Now my research interests are Biomedical/Geographic graph data mining.

My goal as a PhD is to become an independent researcher. I hope to delve into the theory of graph data and graph neural networks, such as robustness, efficiency, and acceleration.

During my spare time, I like to do a variety of sports, like swimming, fitness, and badminton. I’ve recently become addicted to snowboarding, and I’ve tried both single and double boarding.

news

Dec 1, 2023	One 3rd co-authored paper about graph condensation was accepted by ICDE 2024.
Nov 29, 2023	On behalf of my team, I delivered a speech in the data application track of China Mobile’s “Wutong Cup” Big Data Innovation Competition, and won the 2nd place (prize) nationally. Congratulations, my teammates! (China Daily Newspaper, Sina News)
Nov 16, 2023	I won the 2nd prize of “Graduate Student Academic Innovation Award” of Wuhan University (Link).
Oct 26, 2023	One co-authored paper was accepted by Machine Learning.
Oct 25, 2023	I become a reviewer for a paper of Neural Computing and Applications NCAA journal.
Oct 15, 2023	I officially join the Department of Data Science and its Applications (DSA) in German Research Center for Artificial Intelligence (DFKI) as a remote research assistant.
Aug 29, 2023	One co-authored paper was accepted by Knowledge-Based Systems (KBS)!
Jul 26, 2023	One co-authored paper was accepted by ACM MM 2023.
Apr 20, 2023	Congratulations! My paper was accepted by IJCAI 2023! Thanks to my efforts and thanks to my collaborators!
Jan 18, 2023	Congratulations! My first academic paper was accepted by 2023 IEEE International Conference on Communications (ICC2023). It was revised after IJCAI, CIKM, and WSDM.

selected publications

ICC 2023

User and Interaction both Matter: Social Relationship Mining via Interaction Graph Propagating

Yilong Zang, Ruimin Hu, Xixi Li, Zheng Wang, and Dengshi Li

ICC 2023-IEEE International Conference on Communications, 2023

Abs

Social relationship mining benefits many applications such as leadership analysis and advisor recommendation. Existing methods focus on mining user relationships only from the perspective of user-level. To our knowledge, from this perspective, representing the user interactions by edges is not sufficient for the complex information about interactions between users. In addition, mining users’ relationship independently ignores the propagation of social interaction across networks. In this paper, we investigate social relationship mining from a new perspective of interaction-level. We propose an Interaction Graph Propagating(IGP) model which constructs an interaction graph. It not only captures the user interaction information as the union but also exploits the propagation between user interactions. In particular, we utilize the graph attention mechanism to distinguish the contributions of each neighbor union. Experimental results on several public datasets demonstrate that IGP achieves significant improvements over state-of-the-art methods.
IJCAI 2023

Don’t Ignore Alienation and Marginalization: Correlating Fraud Detection

Yilong Zang, Ruimin Hu, Zheng Wang, Danni Xu, Jia Wu, Dengshi Li, Junhang Wu, and Ren Lingfei

In IJCAI 2023, 2023

Abs HTML

The anonymity of online networks makes tackling fraud increasingly costly. Thanks to the superiority of graph representation learning, graph-based fraud detection has made significant progress in recent years. However, upgrading fraudulent strategies produces more advanced and difficult scams. One common strategy is synergistic camouflage —— combining multiple means to deceive others. Existing methods mostly investigate the differences between relations on individual frauds, that neglect the correlation among multi-relation fraudulent behaviors. In this paper, we design several statistics to validate the existence of synergistic camouflage of fraudsters by exploring the correlation among multi-relation interactions. From the perspective of multi-relation, we find two distinctive features of fraudulent behaviors, i.e., alienation and marginalization. Based on the finding, we propose COFRAUD, a correlation-aware fraud detection model, which innovatively incorporates synergistic camouflage into fraud detection. It captures the correlation among multi-relation fraudulent behaviors. Experimental results on two public datasets demonstrate that COFRAUD achieves significant improvements over state-of-the-art methods.