Latent Network Embedding via Adversarial Auto-encoders

TL;DR

This paper introduces a novel adversarial auto-encoder framework for network embedding that uncovers latent structures in graphs, improving tasks like link prediction and node classification.

Contribution

The paper proposes a new latent network embedding model using adversarial auto-encoders to infer hidden network structures from partial observations.

Findings

Achieves superior performance on link prediction tasks.

Improves node classification accuracy.

Demonstrates robustness through adversarial training.

Abstract

Graph auto-encoders have proved to be useful in network embedding task. However, current models only consider explicit structures and fail to explore the informative latent structures cohered in networks. To address this issue, we propose a latent network embedding model based on adversarial graph auto-encoders. Under this framework, the problem of discovering latent structures is formulated as inferring the latent ties from partial observations. A latent transmission matrix that describes the strengths of existing edges and latent ties is derived based on influence cascades sampled by simulating diffusion processes over networks. Besides, since the inference process may bring extra noises, we introduce an adversarial training that works as regularization to dislodge noises and improve the model robustness. Extensive experiments on link prediction and node classification tasks show that the proposed model achieves superior results compared with baseline models.