2 papers
cs.LG2025
Learning Laplacian Positional Encodings for Heterophilous Graphs
Michael Ito, Jiong Zhu, Dexiong Chen +2
In this work, we theoretically demonstrate that current graph positional encodings (PEs) are not beneficial and could potentially hurt performance in tasks involving heterophilous…
cs.LG2024
Learning Long Range Dependencies on Graphs via Random Walks
Dexiong Chen, Till Hendrik Schulz, Karsten Borgwardt
Message-passing graph neural networks (GNNs) excel at capturing local relationships but struggle with long-range dependencies in graphs. In contrast, graph transformers (GTs) enabl…