Develops an exact verification method for GNNs supporting sum, max and mean aggregations via incremental constraint solving with bound tightening for adversarial robustness on node and graph classification tasks.
Mean aggregation In this case, recall that we reduce the original problem to a combination of subproblems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exact Verification of Graph Neural Networks with Incremental Constraint Solving
Develops an exact verification method for GNNs supporting sum, max and mean aggregations via incremental constraint solving with bound tightening for adversarial robustness on node and graph classification tasks.