Network Science | Yujie Zeng

网络科学 ｜ 曾钰洁

Welcome to my homepage.

Yujie Zeng

Yujie Zeng

PhD Candidate

Queen Marry University of London

About Me

I am Yujie Zeng (曾钰洁), a PhD student at Queen Mary University of London, advised by Prof. Athen Ma and Prof. Vito Latora. Previously, I obtained an MSc in Computer Science and Technology from the University of Electronic Science and Technology of China (UESTC), advised by Prof. Linyuan Lü.

My research interests primarily focus on network science, higher-order network analysis, graph representation learning and interdisciplinary applications. 😉

Interests

  • Network Science
  • Higher-order Network
  • Influence Maximization
  • Vital Node Identification
  • Graph Representation Learning

Education

  • Studying in Computing Science, 2024

    Queen Marry University of London

  • MSc in Computer Science and Technology, 2024

    University of Electronic Science and Technology of China (UESTC)

  • BSc in Intelligence Science and Technology, 2021

    Chongqing University of Posts and Telecommunications (CQUPT)

Recent Publications

Influential Simplices Mining via Simplicial Convolutional Networks

Information Processing & Management. Detected an inconsistency between mining influential nodes and simplices. Innovatively formulated the influential simplices mining task as a graph learning problem and designed an influential simplices mining neural network (ISMnet) that achieves SOTA performance in this task.
PDF Dataset DOI Preprint 公众号解读
Influential Simplices Mining via Simplicial Convolutional Networks

Fundamental statistics of higher-order networks: a survey（高阶网络统计指标综述）

物理学报. 本文综述了两种最常见的高阶网络——超图和单纯形网络——常用的统计指标及其物理意义. 本文有助于加深对高阶网络的理解, 促进对高阶网络结构特征的定量化研究, 也有助于研究者在此基础上开发更多适用于高阶网络的统计指标.
Bo liu, Yujie Zeng, Rongmei Yang, Linyuan Lü
PDF DOI 公众号解读

Identifying vital nodes through random walks on higher-order networks

Information Sciences. Developed a Higher-order Augmented Random Walk (HoRW) model to identify influencers, enabling multi-scale analysis according to the strength of higher-order effects.
PDF Code DOI Preprint
Identifying vital nodes through random walks on higher-order networks

Hyper-Null Models and Their Applications

Entropy. This study presents a novel hyperedge swapping method to construct hyper-null models for hypergraphs, which preserves certain network properties while altering others, and demonstrates their applicability in assessing network randomness, statistical properties, and dynamics across multiple datasets.
Yujie Zeng, Bo Liu, Fang Zhou, Linyuan Lü
PDF DOI 公众号解读
Hyper-Null Models and Their Applications

Cooperative Network Learning for Large-Scale and Decentralized Graphs

Developed a cooperative network learning (CNL) framework using technologies like homomorphic encryption, enabling decentralized, multi-party trusted, and privacy-preserving graph learning.
Qiang Wu, Yiming Huang, Yujie Zeng, Yijie Teng, Fang Zhou, Linyuan Lü, (Co-first author)
PDF Code
Cooperative Network Learning for Large-Scale and Decentralized Graphs
See all publications

Talks

Influential Simplices Mining via Simplicial Convolutional Network

Influential Simplices Mining with higher-order GNN model
Jul 12, 2023 Vienna, Austria
PDF
Influential Simplices Mining via Simplicial Convolutional Network

HiGCN: Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes

Higher-order Graph Convolutional Network
May 11, 2023 Chongqing, China

Identifying vital nodes through random walks on higher-order networks

Vital node identification
Jul 28, 2022 12:00 AM Shanghai (Online)
post
Identifying vital nodes through random walks on higher-order networks

Contact