KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification

TL;DR

This paper introduces KGNN, a semi-supervised graph classification model combining GNNs and kernel methods, which effectively leverages unlabeled data to improve performance in graph classification tasks.

Contribution

The paper proposes a novel KGNN model that integrates GNNs with kernel-based networks and jointly trains them using unlabeled data, enhancing semi-supervised graph classification.

Findings

KGNN outperforms existing baselines on benchmark datasets.

Joint training with unlabeled data improves classification accuracy.

Combining GNN and kernel networks captures complementary graph features.

Abstract

This paper studies semi-supervised graph classification, which is an important problem with various applications in social network analysis and bioinformatics. This problem is typically solved by using graph neural networks (GNNs), which yet rely on a large number of labeled graphs for training and are unable to leverage unlabeled graphs. We address the limitations by proposing the Kernel-based Graph Neural Network (KGNN). A KGNN consists of a GNN-based network as well as a kernel-based network parameterized by a memory network. The GNN-based network performs classification through learning graph representations to implicitly capture the similarity between query graphs and labeled graphs, while the kernel-based network uses graph kernels to explicitly compare each query graph with all the labeled graphs stored in a memory for prediction. The two networks are motivated from complementary perspectives, and thus combing them allows KGNN to use labeled graphs more effectively. We jointly train the two networks by maximizing their agreement on unlabeled graphs via posterior regularization, so that the unlabeled graphs serve as a bridge to let both networks mutually enhance each other. Experiments on a range of well-known benchmark datasets demonstrate that KGNN achieves impressive performance over competitive baselines.