Graph Mining

Overview

This course introduces the theory and practice of graph-based data analysis, focusing on complex networks from domains like social media and large-scale systems. Students learn to represent and analyze graphs using models and techniques such as random graph generation, link analysis, centrality measures, community detection, spectral clustering, network diffusion, graph classification, graph embedding, and graph neural networks. Emphasis is placed on uncovering patterns and addressing real-world problems like information spread and influence. Through hands-on assignments with tools like Python, PyTorch, and NetworkX, students build practical skills and prepare to tackle modern challenges in network science, including homophily, influence modeling, and dynamic structure discovery.

Recommended background: Data Structures and Algorithms, Basic ML, Python.