Project Description
Graph neural networks transform the nodes of a graph into a high dimensional latent space.
This project will contrast the distances between nodes of a graph in the input space (graph structure) to their embedding in the latent space.
Queries of interest will be finding node/subgraph outliers, and comparing representations produced by different deep learning methods.
Project can be extended to consider different ways of reducing distortions in embeddings and measuring the local dimensionality of the embedding space.
Note: This project works best with at most 3 people in the group.
Prerequisite Information
Not hard pre-reqs, but recommended CS 24, CS 40, CS 130A
Team Members
- Will Corcoran
- Wyatt Hamabe
- Niyati Mummidivarapu
Professor and Mentors
- Prof. Ambuj Singh
- Grad mentor: Danish Ebadulla
Meeting Times
- Mentor Meetings
- Fridays, 10-11 a.m.
- ERSP Team Meetings
- Mondays, 3:30-5 p.m.