Xi Xiang
Xi Xiang
Success lies in trying.

AI for Complex Networks

~

Welcome to the homepage of AI for Complex Networks !
Tips: The most interesting things in life happen not on individuals, but between them.
——Duncan Watts

Course Introduction

Course number: 05080040 Credit: 1

The teaching content of this course is as follows:

Week Content
Week 12
  • Introduction to the history of complex networks, interdisciplinary thinking, and the integration of network science with artificial intelligence
  • Construction and visualization of network models (e.g., BA network)
Week 13
  • Introduction to AI-based network prediction problems
Week 14
  • Topic 1: Predicting the spread scale of information or rumors using deep learning-based AI methods, with result visualization
Week 15
  • Topic 2: AI-based algorithms for detecting community structure in social networks and corresponding evaluation metrics
  • Community detection on empirical networks with result visualization
Week 16
  • Topic 3: Significance of complex network link prediction
  • Link prediction based on network structure analysis and AI algorithms, with result visualization
Week 17
  • Course discussion and presentations: Students select one topic from three AI applications in complex networks and give an in-class presentation

Course Resourse

Resource of AI for Complex Networks

1. Information Spreading Model

  • Paper: Bin Yang, Ke-ke Shang, Michael Small, Naipeng Chao. (2023) Information overload: How hot topics distract from news—COVID-19 spread in the US. National Science Open, 20220051.
  • DOI: https://doi.org/10.1360/nso/20220051
  • Code & Data: https://box.nju.edu.cn/d/1dd7a23d84cb46fc97a5/
  • Note: Codes for the two-layer network are available on Researchgate.

2. Community Detection

  • Paper: Yijun Ran, Junfan Yi, Wei Si, Michael Small, Ke-ke Shang. Machine learning informed by micro- and mesoscopic statistical physics methods for community detection. *Chaos, 2025, 35(7): 073103.
  • DOI: https://doi.org/10.1063/5.0268930
  • Code & Data: https://github.com/wordbomb/ML-StatisticalPhysics-CommunityDetection
  • Paper: Zi-Xuan Jin, Jun-Fan Yi, Ke-Ke Shang. Learning-based Link Prediction Methods Integrating Network Topological Features and Embedding Representations. *arXiv preprint.
  • arXiv: https://arxiv.org/abs/2512.06677
  • Code & Data: https://github.com/Zi-XuanJin/TELP

Table of Contents