Special Topics in Machine Learning

Enrollment Requirements: Undergraduate Prerequisite: Junior Standing or higher; and (CDSDS 110 and CDSDS 121 and CDSDS 320) Graduate Prerequisite: Graduate Standing Spring 2027 Topic - Graphs in Machine Learning Complex data in many real-world systems, such as social, technological, and biological networks, can often be represented as graphs, where objects are nodes and their relationships are edges. This course introduces key concepts and methods for machine learning with graph-structured data. We begin with foundational ideas in graph theory and classical measures of importance in networks, then explore topics such as graph mining, spectral methods, and graph embeddings. The second half of the course focuses on Graph Neural Networks (GNNs), covering their core principles, representative architectures, and applications to node- and graph-level classification.