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

05/21/2022
by   Wei Ju, et al.
5

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/07/2021

Label Propagation across Graphs: Node Classification using Graph Neural Tangent Kernels

Graph neural networks (GNNs) have achieved superior performance on node ...
research
05/14/2021

Meta-Inductive Node Classification across Graphs

Semi-supervised node classification on graphs is an important research p...
research
07/24/2023

Addressing the Impact of Localized Training Data in Graph Neural Networks

Graph Neural Networks (GNNs) have achieved notable success in learning f...
research
03/16/2017

Shift Aggregate Extract Networks

We introduce an architecture based on deep hierarchical decompositions t...
research
11/08/2022

GENIUS: A Novel Solution for Subteam Replacement with Clustering-based Graph Neural Network

Subteam replacement is defined as finding the optimal candidate set of p...
research
05/31/2023

Towards Semi-supervised Universal Graph Classification

Graph neural networks have pushed state-of-the-arts in graph classificat...
research
02/19/2020

Outcome Correlation in Graph Neural Network Regression

Graph neural networks aggregate features in vertex neighborhoods to lear...

Please sign up or login with your details

Forgot password? Click here to reset