Adversarial training methods for network embedding

Quanyu Dai, Xiao Shen, Liang Zhang, Qiang Li, Dan Wang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

15 Citations (Scopus)

Abstract

Network Embedding is the task of learning continuous node representations for networks, which has been shown effective in a variety of tasks such as link prediction and node classification. Most of existing works aim to preserve different network structures and properties in low-dimensional embedding vectors, while neglecting the existence of noisy information in many real-world networks and the overfitting issue in the embedding learning process. Most recently, generative adversarial networks (GANs) based regularization methods are exploited to regularize embedding learning process, which can encourage a global smoothness of embedding vectors. These methods have very complicated architecture and suffer from the well-recognized non-convergence problem of GANs. In this paper, we aim to introduce a more succinct and effective local regularization method, namely adversarial training, to network embedding so as to achieve model robustness and better generalization performance. Firstly, the adversarial training method is applied by defining adversarial perturbations in the embedding space with an adaptive L2 norm constraint that depends on the connectivity pattern of node pairs. Though effective as a regularizer, it suffers from the interpretability issue which may hinder its application in certain real-world scenarios. To improve this strategy, we further propose an interpretable adversarial training method by enforcing the reconstruction of the adversarial examples in the discrete graph domain. These two regularization methods can be applied to many existing embedding models, and we take DeepWalk as the base model for illustration in the paper. Empirical evaluations in both link prediction and node classification demonstrate the effectiveness of the proposed methods.

Original languageEnglish
Title of host publicationThe Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
PublisherAssociation for Computing Machinery, Inc
Pages329-339
Number of pages11
ISBN (Electronic)9781450366748
DOIs
Publication statusPublished - 13 May 2019
Event2019 World Wide Web Conference, WWW 2019 - San Francisco, United States
Duration: 13 May 201917 May 2019

Publication series

NameThe Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

Conference

Conference2019 World Wide Web Conference, WWW 2019
CountryUnited States
CitySan Francisco
Period13/05/1917/05/19

Keywords

  • Adversarial Training
  • Network Embedding
  • Robustness

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Cite this