A Pure Transformer Pretraining Framework on Text-attributed Graphs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909228016336896 |
|---|---|
| author | Song, Yu Mao, Haitao Xiao, Jiachen Liu, Jingzhe Chen, Zhikai Jin, Wei Yang, Carl Tang, Jiliang Liu, Hui |
| author_facet | Song, Yu Mao, Haitao Xiao, Jiachen Liu, Jingzhe Chen, Zhikai Jin, Wei Yang, Carl Tang, Jiliang Liu, Hui |
| contents | 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 such as feature heterogeneity and structural heterogeneity. Recently, increasing efforts have been made to enhance node feature quality with Large Language Models (LLMs) on text-attributed graphs (TAGs), demonstrating superiority to traditional bag-of-words or word2vec techniques. These high-quality node 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 walks 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, our framework achieves significantly better transferability among graphs within the same domain. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13873 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Pure Transformer Pretraining Framework on Text-attributed Graphs Song, Yu Mao, Haitao Xiao, Jiachen Liu, Jingzhe Chen, Zhikai Jin, Wei Yang, Carl Tang, Jiliang Liu, Hui Artificial Intelligence 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 such as feature heterogeneity and structural heterogeneity. Recently, increasing efforts have been made to enhance node feature quality with Large Language Models (LLMs) on text-attributed graphs (TAGs), demonstrating superiority to traditional bag-of-words or word2vec techniques. These high-quality node 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 walks 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, our framework achieves significantly better transferability among graphs within the same domain. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets. |
| title | A Pure Transformer Pretraining Framework on Text-attributed Graphs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2406.13873 |