-
Hello authors, I have been paying attention to your paper recently, but I followed the steps of your scripts to reproduce the experiment of the Pet part, but found that the effect is not good, the vis…
-
### Description
thank you for expanding the feature importance function with flexible permutation times in the machine learning module in the latest update! While the permutation-based feature import…
-
Dear SHAP authors and contributors,
### Introduction
In this issue, I claim that SHAP Tree algorithm presents a **strong issue** that breaks a **fundamental property** of Shapley values, the **sym…
-
Shapley explanation works for the whole prediction set, however sometimes one needs to explain every step in the forecasting. This is a complex issue due to using different approaches - direct or recu…
-
![image](https://user-images.githubusercontent.com/34906782/179351116-69ef7336-6b79-42ae-9865-60e8e5d5f102.png)
Hi. Sorry to bother you again, I recently tried to use your origin code to reproduce …
-
For some reason, it looks like sgd_shapley is [not performing the Dijkstra projection](https://github.com/ThalesGroup/shapkit/blob/7ad9afb1931a4f903027419d0e461ed4200c3567/shapkit/sgd_shapley.py#L196)…
-
Thank you for this great package! I was trying to replicate what was proposed on the GitHub page, that is:
```
import xgboost
import shap
# train an XGBoost model
X, y = shap.datasets.boston()
…
ghost updated
2 months ago
-
It is a good idea to incorporate the Shapley value into balanced multi-modality learning. However, I couldn't locate the Shapley module in this project. Could you please help me find its location? Tha…
-
Deer author,
Can l use code 'value = self.value(state_, action_pol)' calculate to the credit assignment or Shapley Q-value of each agent?
And the sample size need to be set 1.
Thank you.
-
Introduced in Wu, M., Jia, R., Huang, W., & Chang, X. (2022). [Robust Data Valuation via Variance Reduced Data Shapley](https://arxiv.org/abs/2210.16835). arXiv preprint arXiv:2210.16835.
The idea …