Skip to yearly menu bar Skip to main content


Poster
in
Workshop: New Frontiers in Graph Learning (GLFrontiers)

Higher-Order Expander Graph Propagation

Thomas Christie · Yu He

Keywords: [ long-range dependency ] [ over-squashing ] [ graph neural networks ] [ expander graphs ]


Abstract:

Graph neural networks operate on graph-structured data via exchanging messages along edges. One limitation of this message passing paradigm is the over-squashing problem. Over-squashing occurs when messages from a node's expanded receptive field are compressed into fixed-size vectors, potentially causing information loss. To address this issue, recent works have explored using expander graphs, which are highly-connected sparse graphs with low diameters, to perform message passing. However, current methods on expander graph propagation only consider pair-wise interactions, ignoring higher-order structures in complex data. To explore the benefits of capturing these higher-order correlations while still leveraging expander graphs, we introduce higher-order expander graph propagation. We propose two methods for constructing bipartite expanders and evaluate their performance on both synthetic and real-world datasets.

Chat is not available.