DINE: A Framework for Deep Incomplete Network Embedding

TL;DR

DINE is a novel framework that effectively embeds incomplete networks by completing missing data and leveraging both structure and attributes, outperforming existing methods in classification and prediction tasks.

Contribution

The paper introduces DINE, a deep incomplete network embedding method that combines network completion with joint structure and attribute learning for improved embedding quality.

Findings

DINE outperforms state-of-the-art baselines in multi-label classification.

DINE achieves superior results in link prediction tasks.

The approach effectively handles incomplete network data.

Abstract

Network representation learning (NRL) plays a vital role in a variety of tasks such as node classification and link prediction. It aims to learn low-dimensional vector representations for nodes based on network structures or node attributes. While embedding techniques on complete networks have been intensively studied, in real-world applications, it is still a challenging task to collect complete networks. To bridge the gap, in this paper, we propose a Deep Incomplete Network Embedding method, namely DINE. Specifically, we first complete the missing part including both nodes and edges in a partially observable network by using the expectation-maximization framework. To improve the embedding performance, we consider both network structures and node attributes to learn node representations. Empirically, we evaluate DINE over three networks on multi-label classification and link prediction tasks. The results demonstrate the superiority of our proposed approach compared against state-of-the-art baselines.