Learning in Graph Neural Networks

Speaker: 
Stefanie Jegelka, MIT
Event time: 
Wednesday, March 10, 2021 - 1:00pm
Location: 
Zoom Meeting ID: 97670014308 See map
Event description: 

Abstract: Graph Neural Networks (GNNs) have become a popular tool for learning representations of graph-structured inputs, with applications in computational chemistry, recommendation, pharmacy, reasoning, and many other areas. In this talk, I will show some recent results on learning with message-passing GNNs. In particular, GNNs possess important invariances and inductive biases that affect learning and generalization. We relate these properties and the choice of the “aggregation function” to predictions within and outside the training distribution.

This talk is based on joint work with Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Vikas Garg and Tommi Jaakkola.

email tatianna.curtis@yale.edu for info.

Event Type: 
Applied Mathematics