One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jingzhe, Mao, Haitao, Chen, Zhikai, Li, Bingheng, Fan, Wenqi, Ju, Mingxuan, Zhao, Tong, Shah, Neil, Tang, Jiliang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908383165022208
author Liu, Jingzhe
Mao, Haitao
Chen, Zhikai
Li, Bingheng
Fan, Wenqi
Ju, Mingxuan
Zhao, Tong
Shah, Neil
Tang, Jiliang
author_facet Liu, Jingzhe
Mao, Haitao
Chen, Zhikai
Li, Bingheng
Fan, Wenqi
Ju, Mingxuan
Zhao, Tong
Shah, Neil
Tang, Jiliang
contents Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns, achieving success across different domains. However, existing GNNs require careful domain-specific architecture designs and training from scratch on each dataset, leading to an expertise-intensive process with difficulty in generalizing across graphs from different domains. Therefore, it can be hard for practitioners to infer which GNN model can generalize well to graphs from their domains. To address this challenge, we propose a novel cross-domain pretraining framework, "one model for one graph," which overcomes the limitations of previous approaches that failed to use a single GNN to capture diverse graph patterns across domains with significant gaps. Specifically, we pretrain a bank of expert models, with each one corresponding to a specific dataset. When inferring to a new graph, gating functions choose a subset of experts to effectively integrate prior model knowledge while avoiding negative transfer. Extensive experiments consistently demonstrate the superiority of our proposed method on both link prediction and node classification tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00315
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs
Liu, Jingzhe
Mao, Haitao
Chen, Zhikai
Li, Bingheng
Fan, Wenqi
Ju, Mingxuan
Zhao, Tong
Shah, Neil
Tang, Jiliang
Machine Learning
Artificial Intelligence
Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns, achieving success across different domains. However, existing GNNs require careful domain-specific architecture designs and training from scratch on each dataset, leading to an expertise-intensive process with difficulty in generalizing across graphs from different domains. Therefore, it can be hard for practitioners to infer which GNN model can generalize well to graphs from their domains. To address this challenge, we propose a novel cross-domain pretraining framework, "one model for one graph," which overcomes the limitations of previous approaches that failed to use a single GNN to capture diverse graph patterns across domains with significant gaps. Specifically, we pretrain a bank of expert models, with each one corresponding to a specific dataset. When inferring to a new graph, gating functions choose a subset of experts to effectively integrate prior model knowledge while avoiding negative transfer. Extensive experiments consistently demonstrate the superiority of our proposed method on both link prediction and node classification tasks.
title One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.00315