Pair the Dots: Jointly Examining Training History and Test Stimuli for Model Interpretability

Yuxian Meng
Yuxian Meng
Chun Fan
Chun Fan
Zijun Sun
Zijun Sun
Cited by: 1|Views18

Abstract:

Any prediction from a model is made by a combination of learning history and test stimuli. This provides significant insights for improving model interpretability: {\it because of which part(s) of which training example(s), the model attends to which part(s) of a test example}. Unfortunately, existing methods to interpret a model's pred...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments