arXiv AI September 1, 2026 By Shujie Li, Yuxia Wu, Yuan Fang, Chuan Shi

HeTGB: A Comprehensive Benchmark for Heterophilic Text-Attributed Graphs

HeTGB is a new benchmark for heterophilic text‑attributed graphs, consisting of five real‑world datasets where nodes have rich textual descriptions. It allows systematic evaluation of graph neural networks, pre‑trained language models, and co‑training methods on node classification. The benchmark highlights the utility of text attributes, the challenges of heterophilic TAGs, and the limitations of current models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 24

Semi-Supervised Text-Attributed Graph Distillation

arXiv:2607. 20477v1 Announce Type: new Abstract: {\em Text-Attributed Graphs} (TAGs) have emerged as an expressive data model for integrating graph topology with rich textual semantics.

By Yurui Lai, Samir Moustafa, Renchi Yang, Tsz Nam Chan

llms efficiency benchmarks

arXiv Machine Learning

Aug 26

TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel

arXiv:2606.22975v2 Announce Type: replace Abstract: Text-attributed graphs (TAGs) are widely used in many real-world domains, and learning on TAGs requires jointly modeling text semantics and graph s...

By Yeongho Kim, Yeonje Choi, Kijung Shin

llms efficiency benchmarks

arXiv AI

Aug 18

TAHB: A Comprehensive Benchmark for Text-Attributed Hypergraph Learning

arXiv:2608. 15055v1 Announce Type: new Abstract: Hypergraphs effectively model higher-order groupwise relationships beyond pairwise interactions, while pretrained language models (PLMs) and large language models (LLMs) provide rich semantic understanding from textual attributes.

By David Yoon Suk Kang, JungHyun Kim, Juhyun Jeon, Sang-Wook Kim

llms benchmarks

arXiv Machine Learning

Jul 22

One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models

arXiv:2607. 19128v1 Announce Type: new Abstract: Vision-language models (VLMs) provide a unified representation space for textual and visual information, yet their potential as general-purpose backbones for graph-structured data remains largely unexplored.

By Jiayi Yang, Yifang Chen, Yuanfu Sun, Jiajin Liu, Qiaoyu Tan

llms rag multimodal benchmarks

arXiv Machine Learning

Sep 4

LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models

The paper introduces PromptGFM, a Graph Foundation Model designed for text‑attributed graphs (TAGs). It integrates Large Language Models (LLMs) and Graph Neural Networks (GNNs) through a Graph Understanding Module that prompts LLMs to emulate GNN workflows, and a Graph Inference Module that creates a language‑based graph vocabulary for better alignment and scalability. Experiments show PromptGFM outperforms existing methods and transfers effectively across various graphs and tasks.

By Xi Zhu, Haochen Xue, Ziwei Zhao, Wujiang Xu, Jingyuan Huang, Minghao Guo, Qifan Wang, Kaixiong Zhou, Imran Razzak, Yongfeng Zhang

llms fine-tuning safety

arXiv Machine Learning

Jun 3

Text-attributed Graph Condensation via Text Selection and Attribute Matching

arXiv:2606. 03839v1 Announce Type: new Abstract: Text-Attributed Graph (TAG) is an important type of graph structured data, where each node has a text description.

By Haowei Han, Yuxiang Wang, Guojia Wan, Hao Wang, Shanshan Feng, Hao Huang, Jiawei Jiang, Xiao Yan

llms benchmarks

One email a morning, machine-written

Related stories

Semi-Supervised Text-Attributed Graph Distillation

TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel

TAHB: A Comprehensive Benchmark for Text-Attributed Hypergraph Learning

One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models

LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models

Text-attributed Graph Condensation via Text Selection and Attribute Matching