Saved in:
Bibliographic Details
Main Authors: Bailie, Thomas, Koh, Yun Sing, Mukkavilli, Karthik
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.12052
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909925097078784
author Bailie, Thomas
Koh, Yun Sing
Mukkavilli, Karthik
author_facet Bailie, Thomas
Koh, Yun Sing
Mukkavilli, Karthik
contents Graphs model latent variable relationships in many real-world systems, and Message Passing Neural Networks (MPNNs) are widely used to learn such structures for downstream tasks. While edge-based MPNNs effectively capture local interactions, their expressive power is theoretically bounded, limiting the discovery of higher-order relationships. We introduce the Higher-Order Graph Attention (HoGA) module, which constructs a k-order attention matrix by sampling subgraphs to maximize diversity among feature vectors. Unlike existing higher-order attention methods that greedily resample similar k-order relationships, HoGA targets diverse modalities in higher-order topology, reducing redundancy and expanding the range of captured substructures. Applied to two single-hop attention models, HoGA achieves at least a 5% accuracy gain on all benchmark node classification datasets and outperforms recent baselines on six of eight datasets. Code is available at https://github.com/TB862/Higher_Order.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12052
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HoGA: Higher-Order Graph Attention via Diversity-Aware k-Hop Sampling
Bailie, Thomas
Koh, Yun Sing
Mukkavilli, Karthik
Machine Learning
Graphs model latent variable relationships in many real-world systems, and Message Passing Neural Networks (MPNNs) are widely used to learn such structures for downstream tasks. While edge-based MPNNs effectively capture local interactions, their expressive power is theoretically bounded, limiting the discovery of higher-order relationships. We introduce the Higher-Order Graph Attention (HoGA) module, which constructs a k-order attention matrix by sampling subgraphs to maximize diversity among feature vectors. Unlike existing higher-order attention methods that greedily resample similar k-order relationships, HoGA targets diverse modalities in higher-order topology, reducing redundancy and expanding the range of captured substructures. Applied to two single-hop attention models, HoGA achieves at least a 5% accuracy gain on all benchmark node classification datasets and outperforms recent baselines on six of eight datasets. Code is available at https://github.com/TB862/Higher_Order.
title HoGA: Higher-Order Graph Attention via Diversity-Aware k-Hop Sampling
topic Machine Learning
url https://arxiv.org/abs/2411.12052