Investigating Transfer Learning in Graph Neural Networks

TL;DR

This paper investigates the transferability of graph neural networks (GNNs), demonstrating that transfer learning improves GNN performance, especially when source and target tasks share community structures, with a new methodology and synthetic data generation approach.

Contribution

It provides the first comprehensive analysis of transfer learning in GNNs, introduces a novel synthetic graph task generator, and compares multiple GNN architectures across real and synthetic datasets.

Findings

GNNs with inductive operations significantly improve transfer performance.

Community structure similarity enhances transfer effectiveness.

Transfer learning benefits are consistent across different GNN architectures.

Abstract

Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces. Transfer learning has proven extremely successful for traditional deep learning problems: resulting in faster training and improved performance. Despite the increasing interest in GNNs and their use cases, there is little research on their transferability. This research demonstrates that transfer learning is effective with GNNs, and describes how source tasks and the choice of GNN impact the ability to learn generalisable knowledge. We perform experiments using real-world and synthetic data within the contexts of node classification and graph classification. To this end, we also provide a general methodology for transfer learning experimentation and present a novel algorithm for generating synthetic graph classification tasks. We compare the performance of GCN, GraphSAGE and GIN across both the synthetic and real-world datasets. Our results demonstrate empirically that GNNs with inductive operations yield statistically significantly improved transfer. Further we show that similarity in community structure between source and target tasks support statistically significant improvements in transfer over and above the use of only the node attributes.