aiqbench analysis
This research introduces HeTGB, a new benchmark designed to evaluate Graph Neural Networks on heterophilic text-attributed graphs where connected nodes often belong to different categories. By integrating rich textual descriptions with structural data, the study addresses a critical gap in current GNN literature that typically assumes homophily. The findings offer essential insights for advancing models capable of handling complex, real-world relational data involving both graph topology and natural language attributes.
HeTGB: A Comprehensive Benchmark for Heterophilic Text-Attributed Graphs
arXiv:2503.04822v2 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) have demonstrated success in modeling relational data primarily under the assumption of homophily. However, many real-world graphs exhibit heterophily, where linked nodes belong to different categories or possess diverse attributes, such as webpages, Wikipedia articles, social networks, and e-commerce platforms. Additionally, nodes in many domains are associated with textual descriptions, forming heterophilic text-attributed graphs (TAGs). Despite their significance, heterophilic TAGs remain underexplored due to the lack of dedicated benchmarks that jointly capture heterophilic structures and rich textual attributes. To address this gap, we introduce the \textbf{He}terophilic \textbf{T}ext-attributed \textbf{G}raph \textbf{B}enchmark (HeTGB), a novel benchmark comprising five real-world heterophilic graph datasets from diverse domains, with nodes enriched by extensive textual descriptions. HeTGB enables systematic evaluation of GNNs, pre-trained language models (PLMs) and co-training methods on the node classification task. Through extensive benchmarking experiments, we showcase the utility of text attributes in heterophilic graphs, analyze the challenges posed by heterophilic TAGs and the limitations of existing models, and provide insights into the interplay between graph structures and textual attributes.
Abstract:Graph neural networks (GNNs) have demonstrated success in modeling relational data primarily under the assumption of homophily. However, many real-world graphs exhibit heterophily, where linked nodes belong to different categories or possess diverse attributes, such as webpages, Wikipedia articles, social networks, and e-commerce platforms. Additionally, nodes in many domains are associated with textual descriptions, forming heterophilic text-attributed graphs (TAGs). Despite their significance, heterophilic TAGs remain underexplored due to the lack of dedicated benchmarks that jointly capture heterophilic structures and rich textual attributes. To address this gap, we introduce the \textbf{He}terophilic \textbf{T}ext-attributed \textbf{G}raph \textbf{B}enchmark (HeTGB), a novel benchmark comprising five real-world heterophilic graph datasets from diverse domains, with nodes enriched by extensive textual descriptions. HeTGB enables systematic evaluation of GNNs, pre-trained language models (PLMs) and co-training methods on the node classification task. Through extensive benchmarking experiments, we showcase the utility of text attributes in heterophilic graphs, analyze the challenges posed by heterophilic TAGs and the limitations of existing models, and provide insights into the interplay between graph structures and textual attributes.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2503.04822 [cs.CL]
(or arXiv:2503.04822v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2503.04822 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 266 words
Related coverage
OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation
arXiv · Jul 23, 2026
Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning
arXiv · Oct 5, 2026
Unsupervised Graph Representation Learning with Complementary View Alignment
arXiv · Jul 28, 2026
GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs
arXiv · Jun 12, 2026