Smiley face

 Chuxu Zhang

  Assistant Professor
[CV]
  PhD (University of Notre Dame)
  Email: chuxuzhang[at]brandeis[dot]edu

COSI 241A: Advanced Topics in Graph Mining (Fall 2020, Brandeis)

Course Information

  • Course Description: This course is an advanced level seminar course mainly for graduate students with computer science major or minor degree in the college of arts and sciences. Due to its uniqueness in modeling a variety of real-world complex systems and solving many related problems, graph (mining & learning) has become one of the most important and popular topics in today’s data mining and machine learning community. This course covers recent core techniques and advances in graph mining research. Students read and discuss literature, make presentation, and work on related research projects.
    Topics include: network embedding, graph neural networks, recommendation with graphs, knowledge graphs, and others.
  • Instructor: Chuxu Zhang (chuxuzhang@brandeis.edu)
  • Teaching Assistant: Peizhao Li (peizhaoli@brandeis.edu)
  • Lecture Time: Tuesday/Thursday 4:00pm – 5:30pm
  • Location: Goldsmith 300
  • Office Hour: Appointment
  • Forum: LATTE

Logistics

  • Prerequisites: Background in data mining and machine learning (e.g., COSI 126A, COSI 123A, or COSI 101A) is required, Programming experience in {Python, C/C++, or Java} is required.
  • Course materials: There is no required textbook as it is a seminar course. A list of suggested papers and tutorials will be provided. Class lecture slides will be provided by the instructor and students. Students should make slides for their paper presentations.
  • Grading
    Contributions: Class attendance and participation (10%); Paper reading, presentation, and discussion (40%); Course project with presentation (50%: midterm report 10%, final presentation 10%, final paper 30%)
    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)
  • Statement for Covid-19: Must wear masks and keep social distance during lectures.

Content/Schedule

Date Topic Content (Presenter) Event
8/27 Introduction Introduction (Chuxu Zhang)
9/1 Graph Representation Learning Graph Representation Learning Tutorial 1 (Chuxu Zhang)
9/3 Graph Representation Learning Graph Representation Learning Tutorial 2 (Chuxu Zhang)
9/8 Graph Representation Learning Graph Representation Learning Tutorial 3 (Chuxu Zhang)
9/15 Graph Representation Learning Paper - LINE: Large-Scale Information Network Embedding (Arjun Albert)
Heterogeneous Graph Representation Learning (Chuxu Zhang)
9/17 Graph Representation Learning Paper - Cane: Context-Aware Network Embedding for Relation Modeling (Zhuoran Huang)
Paper - Revisiting Semi-Supervised Learning with Graph Embeddings (Wei Lu)
9/22 Graph Representation Learning Paper - GNNExplainer: Generating Explanations for Graph Neural Networks (Yifei Wang)
Paper - Pte: Predictive Text Embedding Through Large-Scale Heterogeneous Text Networks (Jingxuan Tu)
9/24 Graph Representation Learning Paper - Neural Relational Inference for Interacting Systems (Zhengyang Zhou)
Paper - Strategies for Pre-training Graph Neural Networks (Peizhao Li)
9/29 Graph Representation Learning Paper - Neural Message Passing for Quantum Chemistry (Zizhang Chen)
Grading 1 Release
10/1 Recommendation with Graph Recommendation with Graph Tutorial 1 (Chuxu Zhang)
10/6 Recommendation with Graph Recommendation with Graph Tutorial 2 (Chuxu Zhang)
10/8 Recommendation with Graph Recommendation with Graph Tutorial 3 (Chuxu Zhang)
10/13 Recommendation with Graph Recommendation with Graph Tutorial 4 (Chuxu Zhang)
10/15 Course Project Course Project Midterm Presentation (Students)
10/20 Recommendation with Graph Task-Guided Relation Learning on Heterogeneous Networks (Chuxu Zhang)
10/22 Recommendation with Graph Paper - Heterogeneous Information Network Embedding for Recommendation (Peizhao Li)
Paper - Collaborative Knowledge Base Embedding for Recommender Systems (Zizhang Chen)
10/27 Recommendation with Graph Paper - Reinforcement Knowledge Graph Reasoning for Explainable Recommendation (Wei Lu)
Paper - Explainable Reasoning over Knowledge Graphs for Recommendation (Zhuoran Huang)
10/29 Recommendation with Graph Paper - Personalized Entity Recommendation: A Heterogeneous Information Network Approach (Yifei Wang)
Paper - Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation (Zhengyang Zhou)
11/03 Recommendation with Graph Paper - RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (Jingxuan Tu)
Paper - Representing Multi-Robot Structure through Multimodal Graph Embedding for the Selection of Robot Teams (Arjun Albert)
Grading 2 Release
11/5 Knowledge Graph Knowledge Graph Tutorial 1 (Chuxu Zhang)
11/10 Knowledge Graph Knowledge Graph Tutorial 2 (Chuxu Zhang)
11/12 Knowledge Graph Knowledge Graph Tutorial 3 (Chuxu Zhang)
11/17 Knowledge Graph Paper - KBGAN: Adversarial Learning for Knowledge Graph Embeddings (Jingxuan Tu)
11/19 Knowledge Graph Paper - Embedding Logical Queries on Knowledge Graphs (Zizhang Chen)
Paper - Text Generation from Knowledge Graphs with Graph Transformers (Yifei Wang)
11/24 Knowledge Graph Paper - Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graph (Wei Lu)
Paper - Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs (Peizhao Li)
12/1 Knowledge Graph Paper - Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graph (Zhengyang Zhou)
Paper - An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing (Zhuoran Huang)
Paper - Combining Text Embedding and Knowledge Graph Embedding Techniques for Academic Search Engines (Arjun Albert)
Grading 3 Release
12/3 Course Project Course Project Final Presentation (Students)
Final Report Due: 12/15