Timezone: »

 
Revisiting Robustness in Graph Machine Learning
Lukas Gosch · Daniel Sturm · Simon Geisler · Stephan Günnemann

@
in Trustworthy and Socially Responsible Machine Learning »
Event URL: https://openreview.net/forum?id=lxFHe7CnRY »
Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the studied perturbations always preserve a core assumption of adversarial examples: that of unchanged semantic content. To address this problem, we introduce a more principled notion of an adversarial graph, which is aware of semantic content change. Using Contextual Stochastic Block Models (CSBMs) and real-world graphs, our results uncover: $i)$ for a majority of nodes the prevalent perturbation models include a large fraction of perturbed graphs violating the unchanged semantics assumption; $ii)$ surprisingly, all assessed GNNs show over-robustness - that is robustness beyond the point of semantic change. We find this to be a complementary phenomenon to adversarial robustness related to the small degree of nodes and their class membership dependence on the neighbourhood structure.
[ Poster]  [ OpenReview]  [ Topia] 

Author Information

Lukas Gosch (Technical University of Munich)
Daniel Sturm (Technische Universität München)
Simon Geisler (Technical University of Munich)
Stephan Günnemann (Technical University of Munich)

More from the Same Authors