一个图值$K$个词：使用纯Transformer欧几里得化图
A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
AI总结：
本文提出GraphsGPT框架，通过Graph2Seq编码器将非欧几里得图转换为欧几里得空间中的可学习Graph Words，并用GraphGPT解码器重构原图以确保信息等价，在1亿分子上预训练后在8/9个图分类回归任务达SOTA，并支持少样本和条件图生成。
摘要：
我们能否将非欧几里得图建模为纯语言甚至欧几里得向量，同时保留其固有信息？非欧几里得属性在图建模中构成了长期挑战。尽管近期的图神经网络和图transformer努力将图编码为欧几里得向量，从向量恢复原始图仍具挑战。本文提出GraphsGPT，包含将非欧几里得图转换为欧几里得空间中可学习Graph Words的Graph2Seq编码器，以及从Graph Words重构原始图以确保信息等价的GraphGPT解码器。我们在1亿分子上预训练GraphsGPT并得出有趣发现：(1)预训练的Graph2Seq在图表示学习上表现卓越，在8/9个图分类和回归任务上达到最先进结果。(2)预训练的GraphGPT作为强大的图生成器，在少样本和条件图生成方面均展现出强大能力。(3)Graph2Seq+GraphGPT在欧几里得空间实现有效图混合，克服已知的非欧几里得挑战。(4)边中心预训练框架GraphsGPT在图领域任务中证明其有效性，在表示和生成上均表现优异。代码可在GitHub获取。
英文摘要：
Can we model Non-Euclidean graphs as pure language or even Euclidean vectors while retaining their inherent information? The Non-Euclidean property have posed a long term challenge in graph modeling. Despite recent graph neural networks and graph transformers efforts encoding graphs as Euclidean vectors, recovering the original graph from vectors remains a challenge. In this paper, we introduce GraphsGPT, featuring an Graph2Seq encoder that transforms Non-Euclidean graphs into learnable Graph Words in the Euclidean space, along with a GraphGPT decoder that reconstructs the original graph from Graph Words to ensure information equivalence. We pretrain GraphsGPT on $100$M molecules and yield some interesting findings: (1) The pretrained Graph2Seq excels in graph representation learning, achieving state-of-the-art results on $8/9$ graph classification and regression tasks. (2) The pretrained GraphGPT serves as a strong graph generator, demonstrated by its strong ability to perform both few-shot and conditional graph generation. (3) Graph2Seq+GraphGPT enables effective graph mixup in the Euclidean space, overcoming previously known Non-Euclidean challenges. (4) The edge-centric pretraining framework GraphsGPT demonstrates its efficacy in graph domain tasks, excelling in both representation and generation. Code is available at \href{https://github.com/A4Bio/GraphsGPT}{GitHub}.
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。
