Unifying Node Labels, Features, and Distances for Deep Network Completion.

Qiang Wei,Guangmin Hu

doi:10.3390/e23060771

Abstract

Collected network data are often incomplete, with both missing nodes and missing edges. Thus, network completion that infers the unobserved part of the network is essential for downstream tasks. Despite the emerging literature related to network recovery, the potential information has not been effectively exploited. In this paper, we propose a novel unified deep graph convolutional network that infers missing edges by leveraging node labels, features, and distances. Specifically, we first construct an estimated network topology for the unobserved part using node labels, then jointly refine the network topology and learn the edge likelihood with node labels, node features and distances. Extensive experiments using several real-world datasets show the superiority of our method compared with the state-of-the-art approaches.

Highlights

We begin by introducing the network completion problem with side information; we propose LFD-NC, a deep graph convolutional-network-based algorithm, to solve the problem
We evaluated the performance of LFD-NC on eight real-world network datasets
We treated the prediction of missing edges in Z as a binary classification, and we evaluated the performance of LFD-NC on the basis of two metrics: the area under the ROC curve (AUC) and average precision (AP)

Summary

Introduction

Network structures, such as social networks, web graphs, and communication networks, are important to the functioning of complex systems [1,2]. A complete network structure is a crucial prerequisite for downstream tasks, including node classification and link prediction [3,4,5]. Real-world networks tend to be partially observed, with nodes and edges missing due to insufficient resources and privacy protection [3,6,7]. Social networks, such as Twitter and Facebook, have restrictions for crawlers, which makes it impossible for third-party aggregators to collect complete network data. The collected network structure is often incomplete, which creates difficulties for downstream analysis

Objectives

Methods

Findings

Conclusion