SHAP@ k: Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features

Jan 1, 2024·

Sanjay Kariyappa

,

Leonidas Tsepenekas

,

Freddy Lécué

,

Daniele Magazzeni

· 0 min read

PDF Cite

Type

Conference paper

Publication

Proceedings of the AAAI Conference on Artificial Intelligence

Last updated on Jan 1, 2024

← Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions Jan 1, 2024

Bounding the invertibility of privacy-preserving instance encoding using fisher information Jan 1, 2023 →