Augmentations Graph Edit Operators Node DroppingNode Deletion Edge PerturbationEdge Deletion, Edge Addition Categorical Attribute MaskingFeature Masking Operator Sub-graph SamplingNode Deletions Forexample, consideragraphg A( |g), generated vianodedropping.

Third, weintroduce acomplexitymeasure (seeDefinition 5)thatcharacterizes theoptimal sample complexity of learning in settings (ii) and (iii) above, and we give optimal algorithms for these settings. Finally,wealso provide adaptivelearning algorithms that interpolate between settings (i) and (ii), i.e., whenh is partiallyinvariant.