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

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.

arXiv commentPublished as a full paper at WSDM 2022

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Distilling the Knowledge in a Neural Network
• Neural Message Passing for Quantum Chemistry
• Temporal Ensembling for Semi-Supervised Learning
• Graph Contrastive Learning with Augmentations
• Hierarchical Graph Representation Learning with Differentiable Pooling
• graph2vec: Learning Distributed Representations of Graphs
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• A Survey on Graph Kernels
• Self-Attention Graph Pooling
• Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
• ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction
• Graph Contrastive Learning Automated
• Convolutional Kernel Networks for Graph-Structured Data

Cited by in corpus (5)

• A Comprehensive Survey on Deep Graph Representation Learning
• DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
• Towards Semi-supervised Universal Graph Classification
• GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation
• A Structural Feature-Based Approach for Comprehensive Graph Classification