Compact network embedding for fast node classification

doi:10.1016/j.patcog.2022.109236

Compact network embedding for fast node classification

2023-04-01

4

PRE

AI

DOI：10.1016/j.patcog.2022.109236

Original

Original request for help

Save

Abstract

En 中文

Network embedding has shown promising performance in real-world applications. The network embed-ding typically lies in a continuous vector space, where storage and computation costs are high, especially in large-scale applications. This paper proposes more compact representation to fulfill the gap. The pro-posed discrete network embedding (DNE) leverages hash code to represent node in Hamming space. The Hamming similarity between hash codes approximates the ground-truth similarity. The embedding and classifier are jointly learned to improve compactness and discrimination. The proposed multi-class classi-fier is further constrained to be discrete to expedite classification. In addition, this paper further extends DNE and proposes deep discrete attributed network embedding (DDANE) to learn compact deep embed-ding from more informative attributed network. From the perspective of generalized signal smoothing, the proposed DDANE trains an improved graph convolutional network autoencoder to effectively lever-age node attribute and network structure. Extensive experiments on node classification demonstrate the proposed methods exhibit lower storage and computational complexity than state-of-the-art network em-bedding methods, and achieve satisfactory accuracy.(c) 2022 Elsevier Ltd. All rights reserved.

Keywords:

Network embedding

Hashing

Compact representation

Graph

Compact network embedding for fast node classification

Abstract

Journal

Organization