Robustness meets accuracy in adversarial training for graph autoencoder

Graph autoencoder (GAE) is an effective deep method for graph embedding, while it is vulnerable to the graph adversarial attacks. Adversarial training, which generates adversarial examples in the adversarial scope(neighborhood of natural examples), is effective to improve the robustness of GAE. Howe...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neural networks Ročník 157; s. 114 - 124
Hlavní autoři: Zhou, Xianchen, Hu, Kun, Wang, Hongxia
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States Elsevier Ltd 01.01.2023
Témata:
Adversarial training
Algorithms
Graph autoencoder
Graph embedding
Robustness
Graph autoencoder
Graph embedding
Robustness
Adversarial training
ISSN:0893-6080, 1879-2782, 1879-2782
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Graph autoencoder (GAE) is an effective deep method for graph embedding, while it is vulnerable to the graph adversarial attacks. Adversarial training, which generates adversarial examples in the adversarial scope(neighborhood of natural examples), is effective to improve the robustness of GAE. However, it may lead to degradation of natural accuracy (accuracy on natural examples) due to the extra training examples generated in the adversarial scope (the reasonable scope of adversarial examples). Therefore, considering robustness and natural accuracy is crucial to GAE. In this paper, an improved GAE model is formulated by combining the Structure and Feature encoders, and a novel Adversarial Training strategy (GAE-SFAT) is proposed based on improved GAE. GAE-SFAT has a smaller but more reasonable adversarial scope for adversarial training, which keeps the robustness and reduces the degradation of natural accuracy compared with ordinary adversarial training. In addition, a novel algorithm considering the robustness and accuracy is designed to optimize the GAE-SFAT. We conduct experiments both on the natural graphs as well as perturbed graphs for three datasets. The results show that GAE-SFAT can perform better than state of arts adversarial training model under different kinds of perturbations. •First in the model level, an improved Graph AutoEncoder (GAE) with structure and feature decoders is proposed, which is more reasonable.•Second, a novel adversarial training strategy (GAE-SFAT) is designed, which keeps the robustness and accuracy.•Thirdly experimentally, we show that GAE-SFAT performs well both on the natural and perturbed graphs.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0893-6080
1879-2782
1879-2782
DOI:10.1016/j.neunet.2022.10.010