Graph Machine Learning - CS6804
Fall 2019
Instructor
Overview
This course will provide an introduction to recent research in the area of machine learning for graphs. The course will survey recent approaches to model graph-structured datasets, focusing on fundamental challenges in representation, learning, and inference. The class will be highly interactive, collaborative, and hopefully fun! The bulk of the work will be a class project (which ideally relates to your research and results in a publication), and reading and presenting papers.
Learning objectives
- Learn about Graph Machine Learning
- Work on a research project in the area of Graph Machine Learning
- Sharpen necessary skills for conducting research including: (1) authoring, reviewing and presenting research papers, (2) defining and authoring small research proposals, (3) reviewing a research topic and authoring a research survey paper, (4) participating in research discussions, and (5) collaborating on research.
Background
Suggested background includes machine learning and data analytics. However, course requirements will not be strictly enforced. I expect that students will be coming to the course with a variety of backgrounds and I will be adjusting the course to accommodate that.
Projects
Students are encouraged to propose a project that relates to their research while leveraging graph ML. Other potential projects include: investigating the performance of graph ML algorithms, analyzing data with graph ML models, design and implementation of graph ML model/algorithm extensions, and a survey paper on a chosen problem or class of techniques.
Class Projects
- An empirical comparison between selected supervised graph-based machine learning methods
- Beyond Observed Connections: Link Injection
- Mobile call intensity prediction with graph neural network in a multi-task approach
- Text Generation using HMM, Word2Vec and GraphML
- Auditing Misinformation Recommendation on YouTube
- Improving Programming Learners’ Experience with Graph Machine Learning
- Exploring Link Prediction on Bioinformatics Data
- Representation Learning for Resilient Networks
- Graph Neural Networks for Human Phenotype Ontology Term Prediction in Proteins
- Pre-trained Encoders for Knowledge Base Question-Answering
- Human Object Interaction Detection with Graph Representation
- Stock Price Movement Prediction using Graph ML on Stock Market Correlation Network