Pre-training Graph Neural Networks with Kernels

Abstract

Many machine learning techniques have been proposed in the last few years to process data represented in graph-structured form. Graphs can be used to model several scenarios, from molecules and materials to RNA secondary structures. Several kernel functions have been defined on graphs that coupled with kernelized learning algorithms, have shown state-of-the-art performances on many tasks. Recently, several definitions of Neural Networks for Graph (GNNs) have been proposed, but their accuracy is not yet satisfying. In this paper, we propose a task-independent pre-training methodology that allows a GNN to learn the representation induced by state-of-the-art graph kernels. Then, the supervised learning phase will fine-tune this representation for the task at hand. The proposed technique is agnostic on the adopted GNN architecture and kernel function, and shows consistent improvements in the predictive performance of GNNs in our preliminary experimental results.

References in corpus (5)

• Neural Message Passing for Quantum Chemistry
• Representation Learning on Graphs: Methods and Applications
• Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
• A tree-based kernel for graphs with continuous attributes
• On Filter Size in Graph Convolutional Networks

Cited by in corpus (7)

• Strategies for Pre-training Graph Neural Networks
• Graph Kernels: A Survey
• Graph Clustering with Graph Neural Networks
• Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
• Convolutional Kernel Networks for Graph-Structured Data
• Motif-Driven Contrastive Learning of Graph Representations
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning