← Search

Freddy Lécué

2 accepted papers

2024

Knowledge-Aware Neuron Interpretation for Scene Classification

AAAI 2024technical

Although neural models have achieved remarkable performance, they still encounter doubts due to the intransparency. To this end, model prediction explanation is attracting more and more attentions. However, current methods rarely incorporate external knowledge and still suffer from three limitations…

Cited by 3SourcePDFScholar
2024

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

AAAI 2024technical

The SHAP framework provides a principled method to explain the predictions of a model by computing feature importance. Motivated by applications in finance, we introduce the Top-k Identification Problem (TkIP) (and its ordered variant TkIP- O), where the objective is to identify the subset (or order…

Cited by 3SourcePDFScholar