WalkGAN: Network Representation Learning With Sequence-Based Generative Adversarial Networks

doi:10.1109/TNNLS.2022.3208914

WalkGAN: Network Representation Learning With Sequence-Based Generative Adversarial Networks

2024-04-01

2

PRE

AI

DOI：10.1109/TNNLS.2022.3208914

Original

Original request for help

Save

Abstract

En 中文

Network representation learning, also known as network embedding, aims to learn the low-dimensional representations of vertices while capturing and preserving the network structure. For real-world networks, the edges that represent some important relationships between the vertices of a network may be missed and may result in degenerated performance. The existing methods usually treat missing edges as negative samples, thereby ignoring the true connections between two vertices in a network. To capture the true network structure effectively, we propose a novel network representation learning method called WalkGAN, where random walk scheme and generative adversarial networks (GAN) are incorporated into a network embedding framework. Specifically, WalkGAN leverages GAN to generate the synthetic sequences of the vertices that sufficiently simulate random walk on a network and further learn vertex representations from these vertex sequences. Thus, the unobserved links between the vertices are inferred with high probability instead of treating them as nonexistence. Experimental results on the benchmark network datasets demonstrate that WalkGAN achieves significant performance improvements for vertex classification, link prediction, and visualization tasks.

Keywords:

Generative adversarial networks

Representation learning

Neural networks

Generators

Feature extraction

Task analysis

Learning systems

Generative adversarial networks (GANs)

network representation

random walk

sequence

WalkGAN: Network Representation Learning With Sequence-Based Generative Adversarial Networks

Abstract

Journal

Organization