# Learning Graph Embedding with Adversarial Training Methods

## TL;DR

This paper introduces a novel adversarially regularized framework for graph embedding that improves representation quality by matching latent code distributions to prior distributions, enhancing tasks like link prediction and clustering.

## Contribution

It proposes a new adversarial training approach for graph embedding using GCNs, with two variants ARGA and ARVGA, addressing distribution mismatch issues in existing methods.

## Key findings

- Outperforms twelve algorithms in link prediction tasks.
- Achieves superior results in graph clustering compared to baseline methods.
- Demonstrates the effectiveness of adversarial regularization in graph embedding.

## Abstract

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes, which unfortunately may lead to inferior representation in many cases. In this paper, we present a novel adversarially regularized framework for graph embedding. By employing the graph convolutional network as an encoder, our framework embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph. The adversarial training principle is applied to enforce our latent codes to match a prior Gaussian or Uniform distribution. Based on this framework, we derive two variants of adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively. We also exploit other potential variations of ARGA and ARVGA to get a deeper understanding on our designs. Experimental results compared among twelve algorithms for link prediction and twenty algorithms for graph clustering validate our solutions.