Pre-training Graph Neural Networks with Kernels
This addresses the issue of unsatisfying accuracy in GNNs for graph-structured data, which is incremental as it builds on existing kernel and GNN methods.
The paper tackles the problem of improving Graph Neural Networks (GNNs) accuracy by proposing a task-independent pre-training methodology that allows GNNs to learn representations from state-of-the-art graph kernels, resulting in consistent improvements in predictive performance in preliminary experiments.
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.