Comments (4)
I had the same problem
from xplique.
I found a strange phenomenon. For the same model, the same training sample and test sample, other operations are identical. Theoretically, the values obtained by using the XAI method (like Saliency) to evaluate the interpretability of the model should be the same. However, I retrained a new model, and the interpretability values obtained are completely different from those obtained from the previous model. Does anyone know why this happens? The interpretability value is completely unstable, and the results cannot be reproduced. Unless I completely save this model after training it, and then reload this parameter, the results will be the same.
I have tested two types of prediction tasks: regression and classification. Secondly, I tested 1D-CNN, LSTM, 2D-CNN and other models, and found such problems. For example, I used the for loop to train 10 models under the same conditions. Then, The following command are used for 10 models: explainer = XAI(model) explanations = explainer(X_test, y_test) . The final explanations results will show that the interpretation results for each model are different.
from xplique.
Now my understanding is that even though the prediction accuracy of models trained in the same sample and under the same conditions is almost the same, the difference in the weight parameters (such as neural network) of their own models leads to this result. I don't know if my understanding is correct.
from xplique.
Hi @semihcanturk and @9527-ly ! :)
thank you very much for opening this issue. I proposed a PR (#117) and the new version of Xplique should be available in the day (France). Don't hesitate if you have other problems I'm still available (here is my email in case it's urgent: [email protected]
)
from xplique.
Related Issues (20)
- [BUG] - Error when using tf.data.Dataset on metrics HOT 3
- [Mistakes] - Problems in documentation and SmoothGrad batching
- Interpreting Semantic Segmentations HOT 2
- [BUG] - Can't import the BoundingBoxesExplainer module HOT 1
- [BUG] - new_targets_tf = tf.ones((78,1)) in Attribution methods of regression model HOT 1
- [Enhancement] - Your suggestion/feature request HOT 2
- [BUG] - ndarray not hashable in AverageStability metric HOT 1
- [BUG] - L2 norm missing square root in AverageStability
- [BUG] - Metrics not working with Tensor inputs
- [Enhancement] - Add new attribution method HOT 2
- Documentation : few holes
- Fidelity Metrics with tabular values HOT 5
- Time Series explanation visualization HOT 4
- Fidelity evolution curve visualization HOT 1
- Warning appearing while calling some tabular visualization functions
- Warning appearing while calling some tabular visualization functions HOT 1
- Contribution: Add a protocol to raise issues HOT 3
- [Feature Request] map_to_interpret_space function for Lime and Kernel Shap HOT 6
- [Bug] [Important] attributions of sklearn wrapped models HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from xplique.