Skip to content

Commit 34b32d0

Browse files
committed
2 parents 7ad95bf + 69b8500 commit 34b32d0

20 files changed

+45832
-39608
lines changed

.github/README.md

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,7 @@
22

33
<a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT">
44
<a href="https://standardjs.com"><img src="https://img.shields.io/badge/code_style-standard-brightgreen.svg" alt="Standard - \Python Style Guide"></a>
5+
[![PyPI Downloads](https://static.pepy.tech/badge/xwhy)](https://pepy.tech/projects/xwhy)
56

67
# XWhy: eXplain Why with a <b>SMILE</b> -- <b>S</b>tatistical <b>M</b>odel-agnostic <b>I</b>nterpretability with <b>L</b>ocal <b>E</b>xplanations
78

@@ -12,7 +13,9 @@
1213
<p align="justify">Machine learning is currently undergoing an explosion in capability, popularity, and sophistication. However, one of the major barriers to widespread acceptance of machine learning (ML) is trustworthiness: most ML models operate as black boxes, their inner workings opaque and mysterious, and it can be difficult to trust their conclusions without understanding how those conclusions are reached. Explainability is therefore a key aspect of improving trustworthiness: the ability to better understand, interpret, and anticipate the behaviour of ML models. To this end, we propose a SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains</p>
1314

1415
## News
15-
The SMILE approach has been extended for <b>Point Cloud Explainability</b>. Please check out the examples [here](https://github.com/Dependable-Intelligent-Systems-Lab/xwhy/tree/main/examples/Point%20Cloud%20Examples).
16+
* The SMILE approach has been extended for <b>LLM Explainability</b> by Zeinab Dehghani et al. [Arxiv](https://arxiv.org/pdf/2505.21657v1), [Youtube](https://www.youtube.com/watch?v=pJePjOb2Tj4).
17+
* The SMILE approach has been extended for <b>Point Cloud Explainability</b> by Seyed Mohammad Ahmadi et al. Please check out the examples [here](https://github.com/Dependable-Intelligent-Systems-Lab/xwhy/tree/main/examples/Point%20Cloud%20Examples). [Arxiv](https://arxiv.org/abs/2410.15374), [Youtube](https://www.youtube.com/watch?v=AzYz-JUJTxs).
18+
* The SMILE approach has been extended for <b>Instruction-based Image Editing Explainability</b> by Zeinab Dehghani et al. [Arxiv](https://www.arxiv.org/abs/2412.16277), [Youtube](https://www.youtube.com/watch?v=0QTf2qasrgM&t).
1619

1720
## Installation
1821
```

.gitmodules

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
[submodule "examples/Mapping-the-Mind-of-an-Instruction-based-Image-Editing-using-SMILE"]
2+
path = examples/Mapping-the-Mind-of-an-Instruction-based-Image-Editing-using-SMILE
3+
url = https://github.com/Sara068/Mapping-the-Mind-of-an-Instruction-based-Image-Editing-using-SMILE

Instruct_Pix2Pix.html

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+

examples/x-why-vs-adversarial-attack-on-expl.ipynb renamed to examples/Adversarial_Attacks_Examples/x-why-vs-adversarial-attack-on-expl.ipynb

File renamed without changes.

examples/x-why-image-test-v1-0-0.ipynb renamed to examples/Image_Classification_Examples/x-why-image-test-v1-0-0.ipynb

File renamed without changes.

examples/x-why-image-test-v1-0-0_AK.ipynb renamed to examples/Image_Classification_Examples/x-why-image-test-v1-0-0_AK.ipynb

File renamed without changes.

0 commit comments

Comments
 (0)