EXPLORING ADAPTIVE STRUCTURE LEARNING FOR HETEROPHILIC GRAPHS

ICLR 2025 Workshop ICBINB Submission37 Authors

Track: tiny / short paper (up to 2 pages)

Keywords: Graph Machine Learning, Structure Learning, Geometric Deep Learning, Representation Learning

TL;DR: Employing structure learning on pre-existing vanilla GCN architecture in hope of extracting better node representations for Heterophilic Graph Datasets.

Abstract:

Graph Convolutional Networks (GCNs) gained traction for graph representation
learning, with recent attention on improving performance on heterophilic graphs
for various real-world applications. The localized feature aggregation in a typi-
cal message-passing paradigm hinders the capturing of long-range dependencies
between non-local nodes of the same class. The inherent connectivity structure
in heterophilic graphs often conflicts with information sharing between distant
nodes of same class. We propose structure learning to rewire edges in shallow
GCNs itself to avoid performance degradation in downstream discriminative tasks
due to oversmoothing. Parameterizing the adjacency matrix to learn connections
between non-local nodes and extend the hop span of shallow GCNs facilitates the
capturing of long-range dependencies. However, our method is not generalizable
across heterophilic graphs and performs inconsistently on node classification task
contingent to the graph structure.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 37