GraLSP: Graph Neural Networks with Local Structural Patterns

11/18/2019
by   Yilun Jin, et al.
0

It is not until recently that graph neural networks (GNNs) are adopted to perform graph representation learning, among which, those based on the aggregation of features within the neighborhood of a node achieved great success. However, despite such achievements, GNNs illustrate defects in identifying some common structural patterns which, unfortunately, play significant roles in various network phenomena. In this paper, we propose GraLSP, a GNN framework which explicitly incorporates local structural patterns into the neighborhood aggregation through random anonymous walks. Specifically, we capture local graph structures via random anonymous walks, powerful and flexible tools that represent structural patterns. The walks are then fed into the feature aggregation, where we design various mechanisms to address the impact of structural features, including adaptive receptive radius, attention and amplification. In addition, we design objectives that capture similarities between structures and are optimized jointly with node proximity objectives. With the adequate leverage of structural patterns, our model is able to outperform competitive counterparts in various prediction tasks in multiple datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/25/2020

Graph Structural-topic Neural Network

Graph Convolutional Networks (GCNs) achieved tremendous success by effec...
research
12/21/2019

How Robust Are Graph Neural Networks to Structural Noise?

Graph neural networks (GNNs) are an emerging model for learning graph em...
research
12/24/2022

Multi-duplicated Characterization of Graph Structures using Information Gain Ratio for Graph Neural Networks

Various graph neural networks (GNNs) have been proposed to solve node cl...
research
04/21/2023

What Do GNNs Actually Learn? Towards Understanding their Representations

In recent years, graph neural networks (GNNs) have achieved great succes...
research
04/22/2019

Measuring and Assessing Latent Variation in Alliance Design and Objectives

The alliance literature is bifurcated between an empirically-driven appr...
research
06/11/2021

Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns

Graph neural networks (GNNs) have achieved tremendous success on multipl...
research
11/22/2021

Learnable Structural Semantic Readout for Graph Classification

With the great success of deep learning in various domains, graph neural...

Please sign up or login with your details

Forgot password? Click here to reset