arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.01073cs.LGcs.AI
收藏

图生成预训练Transformer

Graph Generative Pre-trained Transformer

Tufts University(塔夫茨大学);Northeastern University(东北大学);Cornell University(康奈尔大学)

Xiaohui Chen, Yinkai Wang, Jiaxing He, Yuanqi Du, Soha Hassoun, Xiaolin Xu, Li-Ping Liu

AI总结:

本文提出图生成预训练Transformer(G2PT),将图表示为节点集和边集序列,通过自回归下一token预测学习图结构,并在通用图和分子生成及下游任务中展现出优越性能和适应性。

摘要:

图生成在分子设计和社会网络分析等众多领域中是一项关键任务,因为它能够对复杂关系和结构化数据进行建模。虽然大多数现代图生成模型采用邻接矩阵表示,但本文重新审视了一种将图表示为节点集和边集序列的替代方法。我们提倡采用这种方法,因为它能够高效地编码图,并提出了一种新颖的表示方式。基于该表示,我们引入了图生成预训练Transformer(G2PT),这是一种通过下一token预测来学习图结构的自回归模型。为了进一步发挥G2PT作为通用基础模型的能力,我们探索了针对两个下游应用的微调策略:目标导向生成和图性质预测。我们在多个数据集上进行了广泛的实验。结果表明,G2PT在通用图和分子数据集上均取得了优越的生成性能。此外,G2PT在从分子设计到性质预测的下游任务中表现出强大的适应性和多功能性。代码可在https://github.com/tufts-ml/G2PT获取。

英文摘要:

Graph generation is a critical task in numerous domains, including molecular design and social network analysis, due to its ability to model complex relationships and structured data. While most modern graph generative models utilize adjacency matrix representations, this work revisits an alternative approach that represents graphs as sequences of node set and edge set. We advocate for this approach due to its efficient encoding of graphs and propose a novel representation. Based on this representation, we introduce the Graph Generative Pre-trained Transformer (G2PT), an auto-regressive model that learns graph structures via next-token prediction. To further exploit G2PT's capabilities as a general-purpose foundation model, we explore fine-tuning strategies for two downstream applications: goal-oriented generation and graph property prediction. We conduct extensive experiments across multiple datasets. Results indicate that G2PT achieves superior generative performance on both generic graph and molecule datasets. Furthermore, G2PT exhibits strong adaptability and versatility in downstream tasks from molecular design to property prediction. Code available at https://github.com/tufts-ml/G2PT,

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑