Distribution Preserving Graph Representation Learning

02/27/2022
by   Chengsheng Mao, et al.
0

Graph neural network (GNN) is effective to model graphs for distributed representations of nodes and an entire graph. Recently, research on the expressive power of GNN attracted growing attention. A highly-expressive GNN has the ability to generate discriminative graph representations. However, in the end-to-end training process for a certain graph learning task, a highly-expressive GNN risks generating graph representations overfitting the training data for the target task, while losing information important for the model generalization. In this paper, we propose Distribution Preserving GNN (DP-GNN) - a GNN framework that can improve the generalizability of expressive GNN models by preserving several kinds of distribution information in graph representations and node representations. Besides the generalizability, by applying an expressive GNN backbone, DP-GNN can also have high expressive power. We evaluate the proposed DP-GNN framework on multiple benchmark datasets for graph classification tasks. The experimental results demonstrate that our model achieves state-of-the-art performances.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/12/2020

Towards Expressive Graph Representation

Graph Neural Network (GNN) aggregates the neighborhood of each node into...
research
09/02/2022

A Class-Aware Representation Refinement Framework for Graph Classification

Graph Neural Networks (GNNs) are widely used for graph representation le...
research
07/17/2023

Examining the Effects of Degree Distribution and Homophily in Graph Learning Models

Despite a surge in interest in GNN development, homogeneity in benchmark...
research
01/28/2022

Compositionality-Aware Graph2Seq Learning

Graphs are a highly expressive data structure, but it is often difficult...
research
09/29/2021

Equivariant Neural Network for Factor Graphs

Several indices used in a factor graph data structure can be permuted wi...
research
11/15/2021

Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder

The sewerage infrastructure is one of the most important and expensive i...
research
10/23/2019

A Novel Generalized Artificial Neural Network for Mining Two-Class Datasets

A novel general neural network (GNN) is proposed for two-class data mini...

Please sign up or login with your details

Forgot password? Click here to reset