Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-training
This work addresses the problem of generalizing graph pre-training to large-scale industrial graphs for applications like online games, though it is incremental in building on masked autoencoder architectures.
The authors tackled the challenge of extending graph pre-trained models to web-scale graphs with billions of nodes while avoiding negative transfer, by introducing a scalable transformer-based framework called PGT that achieves state-of-the-art performance on a dataset with 111 million nodes and 1.6 billion edges, and scales to real-world graphs with over 540 million nodes and 12 billion edges.
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.