Presents the first certification technique for (non-)robustness of GCNs to L0-bounded perturbations on binary node attributes, together with a joint robust semi-supervised training procedure.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
A new optimization approach for HDC hypervectors minimizes distortion from hardware nonlinearities, delivering up to 48% higher accuracy on QuantHD and 5.4x gains on RelHD under severe perturbations.
citing papers explorer
-
Certifiable Robustness and Robust Training for Graph Convolutional Networks
Presents the first certification technique for (non-)robustness of GCNs to L0-bounded perturbations on binary node attributes, together with a joint robust semi-supervised training procedure.
-
Robust Reasoning and Learning with Brain-Inspired Representations under Hardware-Induced Nonlinearities
A new optimization approach for HDC hypervectors minimizes distortion from hardware nonlinearities, delivering up to 48% higher accuracy on QuantHD and 5.4x gains on RelHD under severe perturbations.
- Graph Navier Stokes Networks