Skip to content

Commit 7ad95bf

Browse files
koo-eckoo-ec
committed
Antigravity Updates
1 parent 6e7201b commit 7ad95bf

19 files changed

+167365
-687
lines changed

‎.vscode/settings.json‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
{
2+
"python.testing.pytestArgs": [
3+
"xwhy"
4+
],
5+
"python.testing.unittestEnabled": false,
6+
"python.testing.pytestEnabled": true
7+
}

‎PointCloud.html‎

Lines changed: 45 additions & 43 deletions
Original file line numberDiff line numberDiff line change
@@ -1,61 +1,61 @@
11
<!DOCTYPE html>
22
<html lang="en">
3+
34
<head>
45
<meta charset="UTF-8">
56
<meta name="description" content="Explainability of Point Cloud Neural Networks Using SMILE">
67
<meta name="keywords" content="XAI, Explainability, SMILE, Point Cloud, SafeML">
78
<meta name="viewport" content="width=device-width, initial-scale=1.0">
89
<title>Explainability with SMILE</title>
910

10-
<!-- Google Analytics -->
11-
<script async src="https://www.googletagmanager.com/gtag/js?id=G-PYVRSFMDRL"></script>
12-
<script>
13-
window.dataLayer = window.dataLayer || [];
14-
function gtag(){ dataLayer.push(arguments); }
15-
gtag('js', new Date());
16-
gtag('config', 'G-PYVRSFMDRL');
17-
</script>
11+
1812

1913
<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">
2014
<link rel="stylesheet" href="./static/css/bulma.min.css">
2115
<link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
2216
<link rel="icon" href="./static/images/favicon.svg">
2317
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
2418
</head>
19+
2520
<body>
2621

27-
<nav class="navbar" role="navigation" aria-label="main navigation">
28-
<div class="navbar-brand">
29-
<a class="navbar-item" href="https://koo-ec.github.io/">
30-
<i class="fas fa-home"></i>
31-
</a>
32-
</div>
33-
</nav>
22+
<nav class="navbar" role="navigation" aria-label="main navigation">
23+
<div class="navbar-brand">
24+
<a class="navbar-item" href="https://koo-ec.github.io/">
25+
<i class="fas fa-home"></i>
26+
</a>
27+
</div>
28+
</nav>
3429

35-
<section class="hero">
36-
<div class="hero-body">
37-
<div class="container">
38-
<h1 class="title">Explainability of Point Cloud Neural Networks Using SMILE</h1>
39-
<p class="subtitle">Statistical Model-Agnostic Interpretability with Local Explanations</p>
40-
<div class="content">
41-
<img src="https://github.com/koo-ec/xwhy/blob/main/docs/graphics/XWhy_Logo_v1.png" alt="XWhy Logo">
30+
<section class="hero">
31+
<div class="hero-body">
32+
<div class="container">
33+
<h1 class="title">Explainability of Point Cloud Neural Networks Using SMILE</h1>
34+
<p class="subtitle">Statistical Model-Agnostic Interpretability with Local Explanations</p>
35+
<div class="content">
36+
<img src="https://raw.githubusercontent.com/koo-ec/xwhy/main/docs/graphics/XWhy_Logo_v1.png" alt="XWhy Logo">
37+
</div>
4238
</div>
4339
</div>
44-
</div>
45-
</section>
40+
</section>
4641

47-
<section class="section">
48-
<div class="container">
49-
<h2 class="title is-3">Abstract</h2>
50-
<p>This study explores the implementation of SMILE for Point Cloud offering enhanced robustness and interpretability, particularly when Anderson-Darling distance is used. The approach demonstrates superior performance in terms of fidelity loss, R<sup>2</sup> scores, and robustness across various kernel widths, perturbation numbers, and clustering configurations.</p>
51-
<p>Additionally, a stability analysis using the Jaccard index establishes a benchmark for model stability in point cloud classification, identifying dataset biases crucial for safety-critical applications like autonomous driving.</p>
52-
</div>
53-
</section>
42+
<section class="section">
43+
<div class="container">
44+
<h2 class="title is-3">Abstract</h2>
45+
<p>This study explores the implementation of SMILE for Point Cloud offering enhanced robustness and
46+
interpretability, particularly when Anderson-Darling distance is used. The approach demonstrates superior
47+
performance in terms of fidelity loss, R<sup>2</sup> scores, and robustness across various kernel widths,
48+
perturbation numbers, and clustering configurations.</p>
49+
<p>Additionally, a stability analysis using the Jaccard index establishes a benchmark for model stability in point
50+
cloud classification, identifying dataset biases crucial for safety-critical applications like autonomous
51+
driving.</p>
52+
</div>
53+
</section>
5454

55-
<section class="section" id="BibTeX">
56-
<div class="container">
57-
<h2 class="title">BibTeX</h2>
58-
<pre><code>
55+
<section class="section" id="BibTeX">
56+
<div class="container">
57+
<h2 class="title">BibTeX</h2>
58+
<pre><code>
5959
@article{aslansefat2024pointcloud,
6060
title={Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanations},
6161
author={Aslansefat, Koorosh and others},
@@ -64,14 +64,16 @@ <h2 class="title">BibTeX</h2>
6464
publisher={IEEE}
6565
}
6666
</code></pre>
67-
</div>
68-
</section>
67+
</div>
68+
</section>
6969

70-
<footer class="footer">
71-
<div class="content has-text-centered">
72-
<p>Licensed under <a href="http://creativecommons.org/licenses/by-sa/4.0/">CC BY-SA 4.0</a>. <a href="https://github.com/koo-ec/xwhy">Source Code</a>.</p>
73-
</div>
74-
</footer>
70+
<footer class="footer">
71+
<div class="content has-text-centered">
72+
<p>Licensed under <a href="http://creativecommons.org/licenses/by-sa/4.0/">CC BY-SA 4.0</a>. <a
73+
href="https://github.com/koo-ec/xwhy">Source Code</a>.</p>
74+
</div>
75+
</footer>
7576

7677
</body>
77-
</html>
78+
79+
</html>

‎README.md‎

Lines changed: 55 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,55 @@
1+
<p align="left"> </p>
2+
3+
<a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT">
4+
<a href="https://standardjs.com"><img src="https://img.shields.io/badge/code_style-standard-brightgreen.svg" alt="Standard - \Python Style Guide"></a>
5+
6+
# X-Why
7+
XWhy: eXplain Why with SMILE -- Statistical Model-agnostic Interpretability with Local Explanations
8+
9+
<p align="center">
10+
<img src="https://github.com/koo-ec/xwhy/blob/main/docs/graphics/XWhy_Logo_v1.png" alt="XWhy, SMILE, Explainability, Interpretability, XAI, machine learning explainability, responsible ai"> </p>
11+
12+
13+
14+
## Installation
15+
```
16+
pip install xwhy
17+
```
18+
19+
## Simple Example
20+
```
21+
import xwhy
22+
import xgboost
23+
24+
# train an XGBoost model
25+
X, y = xwhy.datasets.boston()
26+
model = xgboost.XGBRegressor().fit(X, y)
27+
28+
# explain the model's predictions using xwhy
29+
# (same syntax works for LightGBM, CatBoost, scikit-learn, transformers, Spark, etc.)
30+
explainer = xwhy.Explainer(model)
31+
xwhy_values = explainer(X)
32+
33+
# visualize the first prediction's explanation
34+
xwhy.plots.waterfall(xwhy_values[0])
35+
36+
```
37+
38+
## Citations
39+
It would be appreciated a citation to our paper as follows if you use X-Why for your research:
40+
```
41+
@article{Aslansefat2021Xwhy,
42+
author = {{Aslansefat}, Koorosh and {Hashemian}, Mojgan and {Martin}, Walker and {Papadopoulos}, Yiannis},
43+
title = "{SMILE: Statistical Model-agnostic Interpretability with Local Explanations}",
44+
journal = {arXiv e-prints},
45+
year = {2021},
46+
url = {https://arxiv.org/abs/...},
47+
eprint = {},
48+
}
49+
```
50+
51+
## Acknowledgment
52+
This project is supported by the [Secure and Safe Multi-Robot Systems (SESAME)](https://www.sesame-project.org) H2020 Project under Grant Agreement 101017258.
53+
54+
## Contribution
55+
If you are interested in contributing to this project, please check the [contribution guidelines](https://github.com/koo-ec/xwhy/blob/main/docs/contribute/contributing.md).

‎draft/README.md‎

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

0 commit comments

Comments
 (0)