top of page


Temporal Graphs

Abhinav Chand, Ishika Ghosh, Tristan Freiberg, Astrid Olave Herrera


While Graph Neural Networks have been successful for machine learning on static graphs, many real world graphs are dynamic as the node signals and the connectivity changes with time. We will predict node/ edge labels on dynamic graph using classical graph algorithms, statistical inference, topological data analysis and Temporal Graph Neural Networks. We will work with the Temporal Graph Benchmark for our study and if possible we will apply our models to other real world networks.

Screen Shot 2022-06-03 at 11.31.35 AM.png
github URL
bottom of page