# Kernel Graph Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1710.10689 · HTML: https://mlsanity.com/paper/1710.10689/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2017.

## Built on by (most cited first, 7 of 7)

- [KerGNNs: Interpretable Graph Neural Networks with Graph Kernels](https://mlsanity.com/paper/2201.00491/) (2022)
- [Graph Kernel Neural Networks](https://mlsanity.com/paper/2112.07436/) (2021)
- [State of the Art and Potentialities of Graph-level Learning](https://mlsanity.com/paper/2301.05860/) (2023)
- [Descriptive Kernel Convolution Network with Improved Random Walk Kernel](https://mlsanity.com/paper/2402.06087/) (2024)
- [Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification](https://mlsanity.com/paper/2301.13764/) (2023)
- [Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast](https://mlsanity.com/paper/2106.03723/) (2021)
- [ASD Classification on Dynamic Brain Connectome using Temporal Random Walk with Transformer-based Dynamic Network Embedding](https://mlsanity.com/paper/2503.12366/) (2025)

## Abstract (arXiv)

Graph kernels have been successfully applied to many graph classification problems. Typically, a kernel is first designed, and then an SVM classifier is trained based on the features defined implicitly by this kernel. This two-stage approach decouples data representation from learning, which is suboptimal. On the other hand, Convolutional Neural Networks (CNNs) have the capability to learn their own features directly from the raw data during training. Unfortunately, they cannot handle irregular data such as graphs. We address this challenge by using graph kernels to embed meaningful local neighborhoods of the graphs in a continuous vector space. A set of filters is then convolved with these patches, pooled, and the output is then passed to a feedforward network. With limited parameter tuning, our approach outperforms strong baselines on 7 out of 10 benchmark datasets.