Assistant Professor, PhD
Email: chuxuzhang[at]brandeis[dot]edu
COSI 133A: Graph Mining (Fall 2021, Brandeis)
Course Information
- Course Description: This course is an advanced level course for undergraduates (computer science major) and graduate students in Arts & Sciences. Graph (network) is able to model complex social, technological, and biological systems. This course covers the core concepts, models and algorithms of graph mining technique. Students learn methods of graph mining, apply graph mining tools, and work on related homework and course project. Topics include: machine learning basics, graph basics, graph properties and measures, network models, community analysis, information diffusion, recommendation with graph, heterogeneous information networks, network embedding, graph neural networks and other advanced topics.
- Instructor: Chuxu Zhang (chuxuzhang@brandeis.edu)
- Teaching Assistant: Chunhui Zhang (chunhuizhang@brandeis.edu)
- Lecture Time: Monday/Wednesday 4:00-5:30 PM
- Location: Shapiro Science: 014
- Instructor Office Hour: Tuesday 9-11 PM
- TA Office Hour: Friday 8-10 PM
- Forum: LATTE
- Prerequisites: machine learning (e.g., COSI 123A), proficiency in Python programming.
- Course materials:
Social Media Mining: An Introduction, Reza Zafarani, Mohammad Ali Abbasi and Huan Liu
Graph Representation Learning, William L. Hamilton - Grading
Contributions: class attendance (10%), four programming homeworks (50% = 4 * 12.5%), one course project with presentation (40%: midterm proposal/presentation 10%, final presentation 10%, final report 20%).
Grades (4 points in Brandeis): A (A+) = 4.00; A- = 3.67; B+ = 3.33; B = 3.00; B- = 2.67; C+ = 2.33; C = 2.00; C- = 1.67; D+ = 1.33; D = 1.00; D- = 0.67 and E = 0.00
Grades (100 points): A (A+) = [90, 100]; A- = [87, 90); B+ = [84, 87); B = [81, 84); B- = [78, 81); C+ = [75, 78); C = [72, 75); C- = [69, 72); D+ = [66, 69); D = [63, 66); D- = [60, 63); and E = [0, 60)
Content/Schedule
| Date | Topic | Content | Event |
| 8/30 | Introduction/Background | Introduction of Graph Mining | |
| 9/1 | Introduction/Background | Machine Learning Basics | |
| 9/6, 9/8 | No Lecture | ||
| 9/13 | Introduction/Background | Deep Learning Basics | |
| 9/15 | Graph Basics | Graph Essentials and Measures | First Homework Release |
| 9/20 | Graph Model | Graph Model | |
| 9/22 | Community Analysis | Member-Based Community Detection | |
| 9/27 | No Lecture | ||
| 9/29 | Community Analysis | Group-Based Community Detection | First Homework Due |
| 10/04 | Community Analysis | Dynamic Community Detection | |
| 10/06 | Information Diffusion | Information Diffusion | Second Homework Release |
| 10/11 | Graph Representation Learning | Network Embedding | |
| 10/13 | Graph Representation Learning | Graph Neural Network | |
| 10/18 | Graph Representation Learning | GNN Applications | |
| 10/20 | Graph Representation Learning | Advanced Network Embedding | Second Homework Due |
| 10/25 | Midterm | Project Midterm Presentation | |
| 10/27 | Graph Representation Learning | Advanced Graph Neural Network | |
| 11/01 | Knowledge Graph | Knowledge Graph Embedding | |
| 11/03 | Knowledge Graph | Knowledge Graph Reasoning | Third Homework Release |
| 11/08 | Recommendation with Graph | Basic Recommendation Models | |
| 11/08 | Recommendation with Graph | Deep Learning for Recommendation | |
| 11/15 | Recommendation with Graph | Network Embedding-based Recommendation | |
| 11/17 | Recommendation with Graph | GNN-based Recommendation | Third Homework Due |
| 11/22 | Graph Mining | Review | |
| 11/24 | No Lecture | ||
| 11/29 | Seminar 1 | ||
| 12/01 | Seminar 2 | ||
| 12/06 | Seminar 3 | ||
| 12/08 | Final | Final Project Presentation | Final Report Due: 12/17 |