图的标记化：连接图与变换器

The success of large pretrained Transformers is closely tied to tokenizers that convert raw input into discrete symbols. Extending these models to graph-structured data remains a significant challenge. This research introduces a graph tokenization framework that generates sequential representations of graphs by combining reversible graph serialization, which preserves graph information, with Byte Pair Encoding (BPE), a widely adopted tokenizer in large language models (LLMs). To better capture structural information, the graph serialization process is guided by global statistics of graph substructures, ensuring that frequently occurring substructures appear more often in the sequence and can be merged by BPE into meaningful tokens. Empirical results demonstrate the effectiveness of this approach in processing graph data.