Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains

TL;DR

This paper introduces a diverse set of multi-scale heterogeneous text-attributed graph datasets from multiple domains to facilitate realistic benchmarking of graph neural network models, addressing a significant gap in current research.

Contribution

The authors provide the first comprehensive, multi-domain HTAG datasets with original texts, enabling more realistic evaluation of graph learning methods across various applications.

Findings

Benchmark experiments reveal varying performance of GNNs across domains.

Datasets cover multiple scales and years, reflecting real-world complexity.

Resources are publicly available for reproducibility and further research.

Abstract

Heterogeneous Text-Attributed Graphs (HTAGs), where different types of entities are not only associated with texts but also connected by diverse relationships, have gained widespread popularity and application across various domains. However, current research on text-attributed graph learning predominantly focuses on homogeneous graphs, which feature a single node and edge type, thus leaving a gap in understanding how methods perform on HTAGs. One crucial reason is the lack of comprehensive HTAG datasets that offer original textual content and span multiple domains of varying sizes. To this end, we introduce a collection of challenging and diverse benchmark datasets for realistic and reproducible evaluation of machine learning models on HTAGs. Our HTAG datasets are multi-scale, span years in duration, and cover a wide range of domains, including movie, community question answering, academic, literature, and patent networks. We further conduct benchmark experiments on these datasets with various graph neural networks. All source data, dataset construction codes, processed HTAGs, data loaders, benchmark codes, and evaluation setup are publicly available at GitHub and Hugging Face.