Tag
该论文重新评估了基于LLM的文本属性图节点分类方法，发现其相对简单基线（如Correct & Smooth、MLP）的报告优势往往很小，并记录了测试集调参、标签泄漏等评估风险。
This paper introduces STAG, a stealthy backdoor attack framework targeting graph foundation models on text-attributed graphs, coordinating graph and text triggers to evade detection and achieve effective attacks.
Proposes STAD, a semi-supervised framework for distilling text-attributed graphs using Wasserstein distance, dual-pathway encoders, and LLM-based text synthesis to achieve a state-of-the-art performance-compression trade-off.
This paper proposes LLM-GNN Co-Teaching, a bidirectional framework for few-shot graph learning on text-attributed graphs. The LLM and GNN exchange confident pseudo-labels and use round-based preference optimization (RPL-PO) to mutually improve, outperforming prior methods on benchmarks.