Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/81231
Title: Adversarial training methods for network embedding
Authors: Dai, Q 
Shen, X 
Zhang, L
Li, Q
Wang, D 
Keywords: Adversarial Training
Network Embedding
Robustness
Issue Date: 2019
Publisher: Association for Computing Machinery, Inc
Source: The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019, 2019, p. 329-339 How to cite?
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.
Description: 2019 World Wide Web Conference, WWW 2019, United States, 13-17 May 2019
URI: http://hdl.handle.net/10397/81231
ISBN: 9781450366748
DOI: 10.1145/3308558.3313445
Rights: © 2019 IW3C2 (International World Wide Web Conference Committee). This paper is published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. Authors reserve their rights to disseminate the work on their personal and corporate Web sites with the appropriate attribution.
use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
Dai_Adversarial_Training_Methods.pdf1.14 MBAdobe PDFView/Open
Access
View full-text via PolyU eLinks SFX Query
Show full item record
PIRA download icon_1.1View/Download Contents

Page view(s)

11
Citations as of Oct 22, 2019

Download(s)

3
Citations as of Oct 22, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.