发表机构
National Institute of Informatics（国立情报学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出Acacia，一个仅用Common Crawl Web图从头训练的图基础模型，无需额外训练即可支持多种任务，并具备上下文学习能力，证明图模型可涌现能力。
AI 中文摘要
我们介绍了Acacia，一个在Web图上训练的图基础模型。Acacia（i）无需额外训练即可支持任意特征维度和语义，（ii）无需额外训练即可支持广泛的任务，包括节点分类、链接预测、节点聚类和图生成，（iii）具有上下文学习能力，并且（iv）不依赖预训练的大型语言模型（LLMs）。特别是，现有的图基础模型通常需要训练额外的分类头或特征投影器以适应新图或新标签，而Acacia则不需要。此外，现有的图基础模型通常通过与预训练的LLMs拼接来获得其能力，而Acacia仅使用Common Crawl Web图从头训练。这也是一个重要结果，因为它提供了证据表明图模型可以像LLMs一样从零开始获得涌现能力。
英文摘要
We introduce Acacia, a graph foundation model, trained on the web graph. Acacia (i) supports arbitrary feature dimensionalities and semantics without additional training, (ii) supports a wide range of tasks, including node classification, link prediction, node clustering, and graph generation, without additional training, (iii) has in-context learning capabilities, and (iv) does not rely on pretrained LLMs. In particular, existing graph foundation models often require training additional classification heads or feature projectors to accommodate new graphs or new labels, whereas Acacia does not. Moreover, existing graph foundation models often gain their capabilities by being stitched together with pretrained LLMs, whereas Acacia is trained from scratch using only the Common Crawl web graph. This is also an important result because it provides evidence that graph models can acquire emergent capabilities from scratch like LLMs.
