Sheaf Heterogeneous Neural Networks

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.

Sep 27, 2024 5:00 PM — 5:30 PM

AI Foundations Talk Series