ResearchTrend.AI
Towards Faithful Neural Network Intrinsic Interpretation with Shapley Additive Self-Attribution

Towards Faithful Neural Network Intrinsic Interpretation with Shapley Additive Self-Attribution

Ying Sun
Hengshu Zhu
Huixia Xiong
ArXivPDFHTML

Papers citing "Towards Faithful Neural Network Intrinsic Interpretation with Shapley Additive Self-Attribution"

2 / 2 papers shown
Title
Self-Interpretable Model with TransformationEquivariant Interpretation
Self-Interpretable Model with TransformationEquivariant Interpretation
Yipei Wang
Xiaoqian Wang
24
23
0
09 Nov 2021
FastSHAP: Real-Time Shapley Value Estimation
FastSHAP: Real-Time Shapley Value Estimation
N. Jethani
Mukund Sudarshan
Ian Covert
Su-In Lee
Rajesh Ranganath
TDI
FAtt
59
120
0
15 Jul 2021