Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-training

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: He, Yufei, Hou, Zhenyu, Cen, Yukuo, Hu, Jun, He, Feng, Cheng, Xu, Tang, Jie, Hooi, Bryan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909888331907072
author He, Yufei
Hou, Zhenyu
Cen, Yukuo
Hu, Jun
He, Feng
Cheng, Xu
Tang, Jie
Hooi, Bryan
author_facet He, Yufei
Hou, Zhenyu
Cen, Yukuo
Hu, Jun
He, Feng
Cheng, Xu
Tang, Jie
Hooi, Bryan
contents Graph pre-training has been concentrated on graph-level tasks involving small graphs (e.g., molecular graphs) or learning node representations on a fixed graph. Extending graph pre-trained models to web-scale graphs with billions of nodes in industrial scenarios, while avoiding negative transfer across graphs or tasks, remains a challenge. We aim to develop a general graph pre-trained model with inductive ability that can make predictions for unseen new nodes and even new graphs. In this work, we introduce a scalable transformer-based graph pre-training framework called PGT (Pre-trained Graph Transformer). Based on the masked autoencoder architecture, we design two pre-training tasks: one for reconstructing node features and the other for reconstructing local structures. Unlike the original autoencoder architecture where the pre-trained decoder is discarded, we propose a novel strategy that utilizes the decoder for feature augmentation. Our framework, tested on the publicly available ogbn-papers100M dataset with 111 million nodes and 1.6 billion edges, achieves state-of-the-art performance, showcasing scalability and efficiency. We have deployed our framework on Tencent's online game data, confirming its capability to pre-train on real-world graphs with over 540 million nodes and 12 billion edges and to generalize effectively across diverse static and dynamic downstream tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03953
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-training
He, Yufei
Hou, Zhenyu
Cen, Yukuo
Hu, Jun
He, Feng
Cheng, Xu
Tang, Jie
Hooi, Bryan
Machine Learning
Social and Information Networks
Graph pre-training has been concentrated on graph-level tasks involving small graphs (e.g., molecular graphs) or learning node representations on a fixed graph. Extending graph pre-trained models to web-scale graphs with billions of nodes in industrial scenarios, while avoiding negative transfer across graphs or tasks, remains a challenge. We aim to develop a general graph pre-trained model with inductive ability that can make predictions for unseen new nodes and even new graphs. In this work, we introduce a scalable transformer-based graph pre-training framework called PGT (Pre-trained Graph Transformer). Based on the masked autoencoder architecture, we design two pre-training tasks: one for reconstructing node features and the other for reconstructing local structures. Unlike the original autoencoder architecture where the pre-trained decoder is discarded, we propose a novel strategy that utilizes the decoder for feature augmentation. Our framework, tested on the publicly available ogbn-papers100M dataset with 111 million nodes and 1.6 billion edges, achieves state-of-the-art performance, showcasing scalability and efficiency. We have deployed our framework on Tencent's online game data, confirming its capability to pre-train on real-world graphs with over 540 million nodes and 12 billion edges and to generalize effectively across diverse static and dynamic downstream tasks.
title Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-training
topic Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2407.03953