研究人员正在开发新的图学习方法，这些方法利用或绕过大型语言模型（LLM）。一种名为CANE的方法通过估计条件可靠性来纠正错误，从而解决了LLM生成的标签噪声问题。另一种方法VISION将图少样本学习重新构建为无微调的推理问题，利用受LLM启发的上下文学习能力，但无需直接依赖LLM。第三个框架GILT提供了一个无LLM、无微调的图基础模型，通过基于token的上下文学习机制处理数据异质性，实现高效适应。 AI
影响 这些新的图学习框架在处理复杂、异质图数据方面提供了更高的效率和准确性，有望在推荐系统和网络分析等领域推动应用。
排序理由 该集群包含三篇介绍新图学习方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.27913v1 Announce Type: new Abstract: Node classification on graphs often requires labeled nodes, yet obtaining labels at graph scale is expensive. When node attributes contain semantic content, such as paper abstracts, web pages, or product descriptions, large language…
arXiv:2605.24410v1 Announce Type: new Abstract: Graph few-shot learning, which aims to classify nodes from novel classes with only a few labeled examples, is a widely studied problem in graph learning. However, existing methods often face two key limitations. First, the predomina…
arXiv:2510.04567v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) are powerful tools for processing relational data but often struggle to generalize to unseen graphs, giving rise to the development of Graph Foundational Models (GFMs). However, current GFMs ar…