On Counting Substructures with Graph Neural Networks
Name
tahmasebi-bzt-sm-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
569 KB
Format
Adobe PDF
Checksum (MD5)
23a6d5aae63fac2db65fe0bdb3df1fb1
Author(s)
Tahmasebi, Behrooz
Advisor(s)
Jegelka, Stefanie
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
To achieve a graph representation, most Graph Neural Networks (GNNs) follow two steps: first, each graph is decomposed into a number of subgraphs (which we call the recursion step), and then the collection of subgraphs is encoded by several iterative pooling steps. While recently proposed higher-order networks show a remarkable increase in the expressive power through a single recursion on larger neighborhoods followed by iterative pooling, the power of deeper recursion in GNNs without any iterative pooling is still not fully understood. To make it concrete, we consider a pure recursion-based GNN which we call Recursive Neighborhood Pooling GNN (RNPGNN). The expressive power of an RNP-GNN and its computational cost quantifies the power of (pure) recursion for a graph representation network. We quantify the power by means of counting substructures, which is one main limitation of the Message Passing graph Neural Networks (MPNNs), and show how RNP-GNN can exploit the sparsity of the underlying graph to achieve low-cost powerful representations. We also compare the recent lower bounds on the time complexity and show how recursion-based networks are near optimal.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
