Automated Unsupervised Graph Representation Learning

doi:10.1109/TKDE.2021.3115017

Automated Unsupervised Graph Representation Learning

2021-01-01

6

OA

AI

DOI：10.1109/TKDE.2021.3115017

Original

Original request for help

Save

Abstract

En 中文

Graph data mining has largely benefited from the recent developments of graph representation learning. Most attempts to improve graph representations have thus far focused on designing new network embedding or graph neural network (GNN) architectures. Inspired by the SGC and ProNE models, we instead focus on enhancing any existing or learned graph representations by further smoothing them via graph filters. In this paper, we introduce an automated framework AutoProNE to achieve this. Specifically, AutoProNE automatically searches for a unique optimal set of graph filters for any input dataset, and its existing representations are then smoothed via the selected filters. To make AutoProNE more general, we adopt self-supervised loss functions to guide the optimization of the automated search process. Extensive experiments on eight commonly used datasets demonstrate that the AutoProNE framework can consistently improve the expressive power of graph representations learned by existing network embedding and GNN methods by up to 44%. AutoProNE is also implemented in CogDL, an open source graph learning library, to help boost more algorithms.

Keywords:

Symmetric matrices

Graph neural networks

Convolution

Sparse matrices

Laplace equations

Smoothing methods

Optimization

Representation learning

graph embedding

graph filter

Automated Unsupervised Graph Representation Learning

Abstract

Journal

Organization