README.md 1.6 KB
Newer Older
Avishek Anand's avatar
Ad  
Avishek Anand committed
1 2 3 4 5 6 7 8
## Must-read papers on Interpretability and Explanations.
NRL: network representation learning. NE: network embedding.


We release [InterpretMe]

### Survey papers:

Avishek Anand's avatar
Avishek Anand committed
9 10
1. **Jaspreet's Master Piece**
*Jaspreet Singh* 2019. [paper](https://arxiv.org/pdf/xxx.pdf)
Avishek Anand's avatar
Ad  
Avishek Anand committed
11 12 13 14 15 16 17 18 19 20


### Journal and Conference papers:

1. **Towards a rigorous science of interpretable machine learning.**
*Finale Doshi-Velez and Been Kim.*  2017. [paper]

1. **Streaming weak submodularity: Interpreting neural networks on the fly.**
*Ethan R Elenberg, Alexandros G Dimakis, Moran Feldman, and Amin Karbasi*. 2017 [paper](https://arxiv.org/pdf/1703.02647).

Avishek Anand's avatar
Avishek Anand committed
21 22
1. **Interpretable explanations of black boxes by meaningful perturbation.**
*Ruth C Fong and Andrea Vedaldi.*.CVPR 2017. [paper]
Avishek Anand's avatar
Ad  
Avishek Anand committed
23

Avishek Anand's avatar
Avishek Anand committed
24 25
1. **Supervised topic models for clinical interpretability.**
*Michael C Hughes, Huseyin Melih Elibol, Thomas McCoy, Roy Perlis, and Finale Doshi-Velez.*.2016. [paper](https://arxiv.org/pdf/1612.01678)
Avishek Anand's avatar
Ad  
Avishek Anand committed
26

Avishek Anand's avatar
Avishek Anand committed
27
1. **A unified approach to interpreting model predictions.**
Avishek Anand's avatar
Avishek Anand committed
28
*Scott Lundberg and Su-In Lee.*.2016. [paper](https://arxiv.org/pdf/1705.07874)
Avishek Anand's avatar
Avishek Anand committed
29 30
 
1. **A human-grounded evaluation benchmark for local explanations of machine learning.**
Avishek Anand's avatar
Avishek Anand committed
31
*Sina Mohseni and Eric D Ragan.*.2018. [paper](https://arxiv.org/pdf/1801.05075).
Avishek Anand's avatar
Ad  
Avishek Anand committed
32

Avishek Anand's avatar
Avishek Anand committed
33
1. **Anchors: High-precision model-agnostic explanations.**
Avishek Anand's avatar
Avishek Anand committed
34
*Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin.*.AAAI 2018. [paper]
Avishek Anand's avatar
Ad  
Avishek Anand committed
35

Avishek Anand's avatar
Avishek Anand committed
36
1. **Right for the right reasons: Training differentiable models by constraining their explanations.**
Avishek Anand's avatar
Avishek Anand committed
37
*Andrew Slavin Ross, Michael C. Hughes, and Finale Doshi-Velez.*.IJCAI 2018. [paper](https://doi.org/10.24963/ijcai.2017/371)