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 GNN and
Graphformer efforts encoding graphs as Euclidean vectors, recovering original
graph from the vectors remains a challenge. We introduce GraphsGPT, featuring a
Graph2Seq encoder that transforms non-Euclidean graphs into learnable graph
words in a Euclidean space, along with a GraphGPT decoder that reconstructs the
original graph from graph words to ensure information equivalence. We pretrain
GraphsGPT on 100M molecules and yield some interesting findings: (1) Pretrained
Graph2Seq excels in graph representation learning, achieving state-of-the-art
results on 8/9 graph classification and regression tasks. (2) Pretrained
GraphGPT serves as a strong graph generator, demonstrated by its ability to
perform both unconditional and conditional graph generation. (3)
Graph2Seq+GraphGPT enables effective graph mixup in the Euclidean space,
overcoming previously known non-Euclidean challenge. (4) Our proposed novel
edge-centric GPT pretraining task is effective in graph fields, underscoring
its success in both representation and generation.

我们引入了 GraphsGPT，该模型具有将非欧几里德图转换为学习可表示为欧几里德空间中可学习图词的 Graph2Seq 编码器以及从图词重构原始图以确保信息等价性的 GraphGPT 解码器。我们对 1 亿个分子进行预训练，得出了一些有趣的发现：(1) 预训练的 Graph2Seq 在图表示学习方面表现出色，在 8/9 个图分类和回归任务上取得了最先进的结果。(2) 预训练的 GraphGPT 作为一种强大的图生成器，它能够进行无条件和有条件的图生成。(3) Graph2Seq+GraphGPT 在欧几里德空间中实现了有效的图混合，克服了以前已知的非欧几里德挑战。(4) 我们提出的新型边缘中心 GPT 预训练任务在图领域中非常有效，强调了它在表示和生成方面的成功。