Course Websites

Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: May be repeated in the same or separate terms if topics vary.

This course delves into the exciting field of deep learning for graph-structured data. This course is designed to equip students with an understanding of fundamental principles, classic models, and cutting-edge algorithms, along with practical applications. The curriculum will commence with an exploration of the foundationals, encompassing graph concepts, deep learning fundamentals, node embeddings, and graph neural networks. Building upon this groundwork, the course will progress to advanced topics, including the practical guide for GNN implementation, theories of graph neural networks, and specialized areas such as heterogeneous graphs, knowledge graphs, reasoning mechanisms, and subgraph mining. Moreover, the course will delve into contemporary applications, including graph-based recommender systems, generative models for graphs, graph transformers, and building scalable graph learning systems. The instructional approach will blend traditional lectures, student-led presentations, in