Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

Feng, Fuli; He, Xiangnan; Tang, Jie; Chua, Tat-Seng

doi:10.1109/tkde.2019.2957786

Cited by 143 publications

(94 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some defending works have already appeared. Many of them are inspired by the popular defense methodology in image classification, using adversarial training to protect GNN models, (Feng et al, 2019;Xu et al, 2019), which provides moderate robustness.…”

Section: Defending Graph Neural Networkmentioning

confidence: 99%

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Liu

et al. 2020

Int. J. Autom. Comput.

519

215

View full text Add to dashboard Cite

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i.e., images, graphs and text.

show abstract

Section: Defending Graph Neural Networkmentioning

confidence: 99%

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Liu

et al. 2020

Int. J. Autom. Comput.

519

215

View full text Add to dashboard Cite

show abstract

“…These links which aim characterize anomalous objects and relationships [8]. Graph structure can also be used in adversarial training [9].…”

Section: Introductionmentioning

confidence: 99%

Graph Motif Entropy for Understanding Time-Evolving Networks

Chen

Bai

Wang

et al. 2023

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

The structure of networks can be efficiently represented using motifs, which are those subgraphs that recur most frequently. One route to understanding the motif structure of a network is to study the distribution of subgraphs using statistical mechanics. In this paper, we address the use of motifs as network primitives using the cluster expansion from statistical physics. By mapping the network motifs to clusters in the gas model, we derive the partition function for a network and this allows us to calculate global thermodynamic quantities, such as energy and entropy. We present analytical expressions for the numbers of certain types of motifs, and compute their associated entropy. We conduct numerical experiments for synthetic and real-world data-sets and evaluate the qualitative and quantitative characterizations of the motif entropy derived from the partition function. We find that the motif entropy for real-world networks, such as financial stock market networks, is sensitive to the variance in network structure. This is in line with recent evidence that network motifs can be regarded as basic elements with well defined information-processing functions.

show abstract

“…The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Freund et al [28] proposed an approach based on adversarial regularization of the latent space for generating graph structured data. They could demonstrate the ability of the model to embed graph-based data coherently, and at the same time, generate meaningful samples.…”

Section: Related Workmentioning

confidence: 99%

Data augmentation using generative adversarial neural networks on brain structural connectivity in multiple sclerosis

Barile

Marzullo

Stamile³

et al. 2021

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Background and objective: Machine learning frameworks have demonstrated their potentials in dealing with complex data structures, achieving remarkable results in many areas, including brain imaging. However, a large collection of data is needed to train these models. This is particularly challenging in the biomedical domain since, due to acquisition accessibility, costs and pathology related variability, available datasets are limited and usually imbalanced. To overcome this challenge, generative models can be used to generate new data. Methods: In this study, a framework based on generative adversarial network is proposed to create synthetic structural brain networks in Multiple Sclerosis (MS). The dataset consists of 29 relapsingremitting and 19 secondary-progressive MS patients. T1 and diffusion tensor imaging (DTI) acquisitions were used to obtain the structural brain network for each subject. Evaluation of the quality of newly generated brain networks is performed by (i) analysing their structural properties and (ii) studying their impact on classification performance. Results: We demonstrate that advanced generative models could be directly applied to the structural brain networks. We quantitatively and qualitatively show that newly generated data do not present significant differences compared to the real ones. In addition, augmenting the existing dataset with generated samples leads to an improvement of the classification performance ( 1 81%) with respect to the baseline approach ( 1 66%). Conclusions: Our approach defines a new tool for biomedical application when connectome-based data augmentation is needed, providing a valid alternative to usual image-based data augmentation techniques.

show abstract

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

Cited by 143 publications

References 32 publications

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Graph Motif Entropy for Understanding Time-Evolving Networks

Data augmentation using generative adversarial neural networks on brain structural connectivity in multiple sclerosis

Contact Info

Product

Resources

About