3 papers
cs.LG2025
Random Search Neural Networks for Efficient and Expressive Graph Learning
Michael Ito, Danai Koutra, Jenna Wiens
Random walk neural networks (RWNNs) have emerged as a promising approach for graph representation learning, leveraging recent advances in sequence models to process random walks. H…
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.LG2025
Understanding GNNs and Homophily in Dynamic Node Classification
Michael Ito, Danai Koutra, Jenna Wiens
Homophily, as a measure, has been critical to increasing our understanding of graph neural networks (GNNs). However, to date this measure has only been analyzed in the context of s…