REVIEW 3 cited by
Power up! Robust Graph Convolutional Network via Graph Powering
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Graph convolutional networks (GCNs) are powerful tools for graph-structured data. However, they have been recently shown to be vulnerable to topological attacks. To enhance adversarial robustness, we go beyond spectral graph theory to robust graph theory. By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability. By extending the original graph to a sequence of graphs, we also propose a robust training paradigm that encourages transferability across graphs that span a range of spatial and spectral characteristics. The proposed approaches are demonstrated in extensive experiments to simultaneously improve performance in both benign and adversarial situations.
Forward citations
Cited by 3 Pith papers
-
Transferring Robustness for Graph Neural Network Against Poisoning Attacks
PA-GNN meta-learns to penalize adversarial edges on clean graphs and retains that penalization when fine-tuned on a poisoned graph, improving node classification accuracy under poisoning attacks.
-
Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors
Under a fixed leakage-free protocol, NC→LP transfer reliably helps on homophilic graphs while LP→NC helps mainly when LP is easy and NC is unsaturated; homophily and CoTask Score guide mechanism choice.
-
AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models
AdaGCN applies AdaBoost to combine non-linear classifiers trained on A^l X features from each hop, achieving state-of-the-art node classification on several benchmarks while avoiding the oversmoothing that limits deep...
Discussion (0). Continue with ORCID to comment.