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.
By Shujie Li, Yuxia Wu, Yuan Fang, Chuan Shi
arXiv:2609.36902v1 Announce Type: new
Abstract: Existing multimodal fake news detection methods often introduce external information to assist detection. However, most of them rely on entity-level re...
By Wenbin Shen, Guoxuan Qin, Guangxu Yao, Baodong Wang, Yuanbo Rui, Zhongjie Ba, Zhichao Lian
arXiv:2607. 11894v1 Announce Type: cross Abstract: Detecting disinformation narratives on social media is challenging due to the scale of amplification, rapid evolution, and linguistic variability of online content.
By Yuliia Vistak, Viktoriia Makovska, Vera Schmitt, Veronika Solopova
The paper reinterprets graph neural networks (GNNs) as retrieval-augmented models, where each layer uses an MLP on a node representation and a permutation‑invariant summary of retrieved graph context instead of traditional message passing. It introduces RTA, a lightweight MLP‑based framework that replaces structural message passing with label‑aware retrieval and propagation, and provides theoretical links to softmax‑attention message passing and robustness to mis‑retrieved outliers. Experiments on text‑attributed graph benchmarks demonstrate that RTA matches or surpasses strong GNN and graph LLM baselines while improving efficiency and robustness.
By Jintang Li, Yuhong Chen, Ruofan Wu, Binli Luo, Jiayi Ji, Hui Li, Rongrong Ji
arXiv:2609.36850v1 Announce Type: new
Abstract: Generative content is increasingly entering the production and dissemination of news, transforming fake news from manually fabricated or simply manipul...
By Wenbin Shen, Guoxuan Qin, Guangxu Yao, Baodong Wang, Yuanbo Rui, Zhichao Lian
The paper introduces the Echo Chamber Effect, a failure mode in Graph Neural Networks where intra-community representations collapse while inter-community separation remains, differing from traditional oversmoothing. It proposes the Echo Chamber Index (ECI) to detect this effect by stratifying pairwise distances by community membership. Building on this analysis, the authors present Community-Aware Split Propagation (CASP), a lightweight plugin that decouples intra- and inter-community aggregation and learns their balance from label structure, improving performance across various GNN backbones in both homophilic and heterophilic settings.
By Asela Hevapathige, Ahad N. Zehmakan, Asiri Wijesinghe, Saman Halgamuge
Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text. However, real-world TAGs are often imperfect, with quality issues arising from text, structure, and labels, and typically manifesting as sparsity, noise, and imbalance.
arXiv:2601. 02366v3 Announce Type: replace-cross Abstract: Graph-based recommendation has achieved great success in recent years.
By Yiwen Chen, Yiqing Wu, Huishi Luo, Fuzhen Zhuang, Deqing Wang, Zhao Zhang
arXiv:2609.24219v1 Announce Type: new
Abstract: Traditionally, the reliability of news publishers is assessed by expert organisations that evaluate editorial practices, transparency and factual stand...
By John Bianchi, Manuel Pratelli, Fabio Pinelli, Marinella Petrocchi
arXiv:2607. 19108v1 Announce Type: new Abstract: Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text.
By Yuze Dai, Zhihan Zhang, Yan Zhao, Ruoyu Wu, Xunkai Li, Zekai Chen, Qiangqiang Dai, Hongchao Qin, Ronghua Li
arXiv:2606. 31166v1 Announce Type: cross Abstract: Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology.
By Lingjie Chen, Yuanchen Bei, Haobo Xu, Yanjun Zhao, Yuzhong Chen, Hanghang Tong
TH-GNN is a heterogeneous temporal graph neural network designed to detect shilling attacks generated by large language model (LLM) agents. It combines a two‑layer Heterogeneous Graph Transformer with per‑type and per‑relation attention, learnable sinusoidal temporal encodings, cross‑modal attention that fuses user embeddings with frozen RoBERTa representations of reviews and item descriptions, and a GRU that models log inter‑arrival times. Across five attack families and four benchmark datasets, TH‑GNN achieves a grand‑mean F1 score of 0.870, surpassing the best text‑only baseline on Agent4SR attacks by 10.9 percentage points and 11.5 percentage points at the lowest injection rate.
By Shivam Swarup, Divya Prakash Shrivastava, Rakesh Thakur