Spectrally unstable nodes are identified via graph-spectral distortion analysis as primary drivers of reliability failures; isolating them yields a stable subgraph for learning with propagation-based recovery for the isolated nodes, improving performance across GNNs and spectral clustering under攻击s.
Ml-loo: Detecting ad- versarial examples with feature attribution,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spectrally unstable nodes drive reliability failures in graph learning
Spectrally unstable nodes are identified via graph-spectral distortion analysis as primary drivers of reliability failures; isolating them yields a stable subgraph for learning with propagation-based recovery for the isolated nodes, improving performance across GNNs and spectral clustering under攻击s.