Sheaves for Heterogeneous Data

Add to your list(s) Download to your calendar using vCal

• Luke Braithwaite
• Friday 27 September 2024, 17:00-18:00
• Lecture Theatre 2, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Pietro Lio.

Heterogeneous graphs, with nodes and edges of different types, are commonly used to model relational structures in many real-world applications, such as social networks, recommendation systems, and bioinformatics. Current heterogeneous graph neural networks have focused on accounting for the heterogeneity in the model architecture, leading to increasingly complex models. This talk discusses a novel approach that uses cellular sheaves to model the heterogeneity in the graph’s underlying topology and achieves competitive benchmark results while being more parameter-efficient.

This talk is part of the Foundation AI series.

This talk is included in these lists:

• Lecture Theatre 2, Computer Laboratory, William Gates Building

Note that ex-directory lists are not shown.