A Pure Transformer Pretraining Framework on Text-attributed Graphs

Pretraining plays a pivotal role in acquiring generalized knowledge from large-scale data, achieving remarkable successes as evidenced by large models in CV and NLP. However, progress in the graph domain remains limited due to fundamental challenges represented by feature heterogeneity and structural heterogeneity. Recent efforts have been made to address feature heterogeneity via Large Language Models (LLMs) on text-attributed graphs (TAGs) by generating fixed-length text representations as node features. These high-quality features reduce the previously critical role of graph structure, resulting in a modest performance gap between Graph Neural Networks (GNNs) and structure-agnostic Multi-Layer Perceptrons (MLPs). Motivated by this, we introduce a feature-centric pretraining perspective by treating graph structure as a prior and leveraging the rich, unified feature space to learn refined interaction patterns that generalizes across graphs. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walk and employs masked feature reconstruction to capture pairwise proximity in the LLM-unified feature space using a standard Transformer. By utilizing unified text representations rather than varying structures, GSPT alleviates structural heterogeneity and achieves significantly better transferability among graphs within the same domain. Our approach can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets. The source code is publicly available at https://github.com/SongYYYY/GSPT.