# Pre-training Graph Neural Networks with Kernels

arXiv: https://arxiv.org/abs/1811.06930 · HTML: https://mlsanity.com/paper/1811.06930/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [Self-supervised Graph-level Representation Learning with Local and Global Structure](https://mlsanity.com/paper/2106.04113/) (2021)
- [KerGNNs: Interpretable Graph Neural Networks with Graph Kernels](https://mlsanity.com/paper/2201.00491/) (2022)
- [MentorGNN: Deriving Curriculum for Pre-Training GNNs](https://mlsanity.com/paper/2208.09905/) (2022)
- [Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?](https://mlsanity.com/paper/2412.08174/) (2024)
- [A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective](https://mlsanity.com/paper/2403.16137/) (2024)
- [Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning](https://mlsanity.com/paper/2103.00771/) (2021)
- [Descriptive Kernel Convolution Network with Improved Random Walk Kernel](https://mlsanity.com/paper/2402.06087/) (2024)
- [Graph Prompting for Graph Learning Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2506.08326/) (2025)

## Abstract (arXiv)

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.