Fast Network Embedding Enhancement via High Order Proximity Approximation

By Cheng Yang, Maosong Sun, Zhiyuan Liu, Cunchao Tu. 2017

155 citations recorded by the source corpus.

Many Network Representation Learning (NRL) methods have been proposed to learn vector representations for vertices in a network recently. In this paper, we summarize most existing NRL methods into a unified two-step framework, including proximity matrix construction and dimension reduction. We focus on the analysis of proximity matrix construction step and conclude that an NRL method can be improved by exploring higher order proximities when building the proximity matrix. We propose Network Embedding Update (NEU) algorithm which implicitly approximates higher order proximities with theoretical approximation bound and can be applied on any NRL methods to enhance their performances. We conduct experiments on multi-label classification and link prediction tasks. Experimental results show that NEU can make a consistent and significant improvement over a number of NRL methods with almost negligible running time on all three publicly available datasets. The source code of this paper can be obtained from https://github.com/thunlp/NEU.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, methodology): “[146] provide a fast embedding approach by approxi-”
Attention-based Graph Neural Network for Semi-supervised Learning (2018, neutral): “Yang et al. [45] provide a post-processing scheme that takes any node embedding and attempts to improve it by by taking the weighted sum of the given embeddings with Personalized PageRank weights.”
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec (2017, methodology): “Discussion on Yang et al. [46, 47] Two related works we want to discuss here are [46] and [47] by the same authors, where they claim they prove a closed form matrix factorized by DeepWalk. conclusion is then referred and used in a few following papers [29, 42, 48].”
Under review as a conference paper at ICLR 2019 MILE : A Multi-Level Framework for Scalable Graph Embedding (2018, unknown): “On the other hand, there are very few efforts, focusing on the scalability of network embedding (Yang et al., 2017; Huang et al., 2017).”