Skip to main content
Search

# Deletion Sufficiency

1 related articles

Subscribe to updates
  1. arXiv

    Sufficient explanations can be impossible: nine of ten classification datasets contain co-bounds that block any sufficient explainer

    For structured inputs such as graphs and strings, post-hoc explainers often select part of the input as a sufficient explanation, meaning that part alone guarantees the prediction. A formal framework places what an explainer may select and the classifier side by side and shows that a sufficient explainer exists exactly when there is no co-bound, an instance selectable from a differently labeled instance. Across ten language, protein, peptide and molecular classification datasets, nine contain co-bounds; ENZYMES has only 2.2% of instances as co-bounds, yet removing them requires relabeling 82% of its instances.

You’re all caught up