Saved in:
Bibliographic Details
Main Authors: Ly, Khang, Kashnitsky, Yury, Chamezopoulos, Savvas, Krzhizhanovskaya, Valeria
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.11341
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913366070525952
author Ly, Khang
Kashnitsky, Yury
Chamezopoulos, Savvas
Krzhizhanovskaya, Valeria
author_facet Ly, Khang
Kashnitsky, Yury
Chamezopoulos, Savvas
Krzhizhanovskaya, Valeria
contents Classifying research output into context-specific label taxonomies is a challenging and relevant downstream task, given the volume of existing and newly published articles. We propose a method to enhance the performance of article classification by enriching simple Graph Neural Network (GNN) pipelines with multi-graph representations that simultaneously encode multiple signals of article relatedness, e.g. references, co-authorship, shared publication source, shared subject headings, as distinct edge types. Fully supervised transductive node classification experiments are conducted on the Open Graph Benchmark OGBN-arXiv dataset and the PubMed diabetes dataset, augmented with additional metadata from Microsoft Academic Graph and PubMed Central, respectively. The results demonstrate that multi-graphs consistently improve the performance of a variety of GNN models compared to the default graphs. When deployed with SOTA textual node embedding methods, the transformed multi-graphs enable simple and shallow 2-layer GNN pipelines to achieve results on par with more complex architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2309_11341
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Article Classification with Graph Neural Networks and Multigraphs
Ly, Khang
Kashnitsky, Yury
Chamezopoulos, Savvas
Krzhizhanovskaya, Valeria
Machine Learning
Computation and Language
Classifying research output into context-specific label taxonomies is a challenging and relevant downstream task, given the volume of existing and newly published articles. We propose a method to enhance the performance of article classification by enriching simple Graph Neural Network (GNN) pipelines with multi-graph representations that simultaneously encode multiple signals of article relatedness, e.g. references, co-authorship, shared publication source, shared subject headings, as distinct edge types. Fully supervised transductive node classification experiments are conducted on the Open Graph Benchmark OGBN-arXiv dataset and the PubMed diabetes dataset, augmented with additional metadata from Microsoft Academic Graph and PubMed Central, respectively. The results demonstrate that multi-graphs consistently improve the performance of a variety of GNN models compared to the default graphs. When deployed with SOTA textual node embedding methods, the transformed multi-graphs enable simple and shallow 2-layer GNN pipelines to achieve results on par with more complex architectures.
title Article Classification with Graph Neural Networks and Multigraphs
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2309.11341