Learning Robust Node Representation on Graphs

08/26/2020
by   Xu Chen, et al.
10

Graph neural networks (GNN), as a popular methodology for node representation learning on graphs, currently mainly focus on preserving the smoothness and identifiability of node representations. A robust node representation on graphs should further hold the stability property which means a node representation is resistant to slight perturbations on the input. In this paper, we introduce the stability of node representations in addition to the smoothness and identifiability, and develop a novel method called contrastive graph neural networks (CGNN) that learns robust node representations in an unsupervised manner. Specifically, CGNN maintains the stability and identifiability by a contrastive learning objective, while preserving the smoothness with existing GNN models. Furthermore, the proposed method is a generic framework that can be equipped with many other backbone models (e.g. GCN, GraphSage and GAT). Extensive experiments on four benchmarks under both transductive and inductive learning setups demonstrate the effectiveness of our method in comparison with recent supervised and unsupervised models.

READ FULL TEXT

page 7

page 16

research
03/18/2020

Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization

Graph representation learning based on graph neural networks (GNNs) can ...
research
09/02/2022

A Novel Approach for Pill-Prescription Matching with GNN Assistance and Contrastive Learning

Medication mistaking is one of the risks that can result in unpredictabl...
research
05/27/2022

Bayesian Robust Graph Contrastive Learning

Graph Neural Networks (GNNs) have been widely used to learn node represe...
research
10/08/2020

Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models

Existing Graph Neural Network (GNN) methods that learn inductive unsuper...
research
09/06/2023

Towards Unsupervised Graph Completion Learning on Graphs with Features and Structure Missing

In recent years, graph neural networks (GNN) have achieved significant d...
research
05/17/2022

KGNN: Distributed Framework for Graph Neural Knowledge Representation

Knowledge representation learning has been commonly adopted to incorpora...
research
05/20/2022

Tackling Provably Hard Representative Selection via Graph Neural Networks

Representative selection (RS) is the problem of finding a small subset o...

Please sign up or login with your details

Forgot password? Click here to reset