2019

Edge Dithering for Robust Adaptive Graph Convolutional Networks

Ioannidis, Vassilis N., Giannakis, Georgios B.

Understand

Graph convolutional networks (GCNs) are vulnerable to perturbations of the graph structure that are either random, or, adversarially designed.

The perturbed links modify the graph neighborhoods, which critically affects the performance of GCNs in semi-supervised learning (SSL) tasks.
Aiming at robustifying GCNs conditioned on the perturbed graph, the present paper generates multiple auxiliary graphs, each having its binary 0-1 edge weights flip values with probabilities designed to enhance robustness.
The resultant edge-dithered auxiliary graphs are leveraged by an adaptive (A)GCN that performs SSL.

R. A. Ulichney, “Dithering with blue noise,”
1988
Earlier work this paper cites.
S. Wasserman and K. Faust,
1994
Earlier work this paper cites.
A. J. Smola and R. I. Kondor, “Kernels and regularization on graphs,” in
2003
Earlier work this paper cites.
X. Zhu, Z. Ghahramani, and J. D. Lafferty, “Semi-supervised learning using gaussian fields and harmonic functions,” in
2003
Earlier work this paper cites.
M. Belkin, P. Niyogi, and V. Sindhwani, “Manifold regularization: A geometric framework for learning from labeled and unlabeled examples,”
2006
Earlier work this paper cites.
P. Sen, G. Namata, M. Bilgic, L. Getoor, B. Galligher, and T. Eliassi-Rad, “Collective classification in network data,”
2008
Earlier work this paper cites.
I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” in
2014
Earlier work this paper cites.
M. Kivelä, A. Arenas, M. Barthelemy, J. P. Gleeson, Y. Moreno, and M. A. Porter, “Multilayer networks,”
2014
Earlier work this paper cites.
L. Akoglu, H. Tong, and D. Koutra, “Graph based anomaly detection and description: a survey,”
2015
Earlier work this paper cites.
C. C. Aggarwal, “Outlier analysis,” in
2015
Earlier work this paper cites.

D. P. Kingma and J. L. Ba, “Adam: A method for stochastic optimization,” in
2015
Cited alongside, same era.
Y. Yan, Z. Xu, I. W. Tsang, G. Long, and Y. Yang, “Robust semi-supervised learning through label aggregation,” in
2016
Cited alongside, same era.
I. Goodfellow, Y. Bengio, A. Courville, and Y. Bengio,
2016
Cited alongside, same era.
S. Cao, W. Lu, and Q. Xu, “Deep neural networks for learning graph representations,” in
2016
Cited alongside, same era.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in
2016
Cited alongside, same era.
T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in
2017
Cited alongside, same era.
M. M. Bronstein, J. Bruna, Y. LeCun, A. Szlam, and P. Vandergheynst, “Geometric deep learning: going beyond euclidean data,”
2017
Cited alongside, same era.
M. Zitnik and J. Leskovec, “Predicting multicellular function through multi-layer tissue networks,”
2017
Cited alongside, same era.
D. Dheeru and E. Karra Taniskidou, “UCI machine learning repository,” 2017. [Online]. Available:
2017
Cited alongside, same era.

D. Zügner, A. Akbarnejad, and S. Günnemann, “Adversarial attacks on neural networks for graph data,” in
2018
Later among the works it cites.
P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio, “Graph attention networks,” in
2018
Later among the works it cites.
H. Dai, H. Li, T. Tian, X. Huang, L. Wang, J. Zhu, and L. Song, “Adversarial attack on graph structured data,” in
2018
Later among the works it cites.
R. Li, S. Wang, F. Zhu, and J. Huang, “Adaptive graph convolutional neural networks,” in
2018
Later among the works it cites.
J. Ye and L. Akoglu, “Robust semi-supervised learning on multiple networks with noise,” in
2018
Later among the works it cites.
K. Xu, W. Hu, J. Leskovec, and S. Jegelka, “How powerful are graph neural networks?” in
2019
Closest in time.
K. Xu, H. Chen, S. Liu, P.-Y. Chen, T.-W. Weng, M. Hong, and X. Lin, “Topology attack and defense for graph neural networks: An optimization perspective,” in
2019
Closest in time.
H. Wu, C. Wang, Y. Tyshetskiy, A. Docherty, K. Lu, and L. Zhu, “Adversarial examples on graph data: Deep insights into attack and defense,” in
2019
Closest in time.
D. Zhu, Z. Zhang, P. Cui, and W. Zhu, “Robust graph convolutional networks against adversarial attacks,” in
2019
Closest in time.

alphaXiv searches the wider corpus for related work and actual follow-ups.

alphaXiv is searching for related work…

Reading the bibliography…