-
I'm seeing that the order of the dataset being used matters while calculating the shapley values. Is that the case ?
Sample code
```python
import numpy as np
import pandas as pd
import xgboost…
-
-
`UnivariateFinite` can be overkill for e.g. simple `Bool` categories.
It looks like they could be at least 50x faster to construct using a custom struct without the `LittleDict`.
Adding a `Abst…
-
TMC-Shapley algorithm in the paper says that the model is trained for each new datum that is added to the batch. However, in the line below the model is trained only when the batch size is the same as…
-
Hi,
I try to run the code with
```
python refine.py --dataset cora \
--solve-proxy-epochs 200 \
--solve-proxy-eval-every 20 \
--solve-proxy-node-lr 1e-2 \
--solve-proxy-edge-lr …
J-zin updated
2 years ago
-
Hi @slundberg,
First of all, thank you and all your collaborators for the amazing work on OpenSourcing the SHAP module. It has proven very useful for my research!
Currently, I am using the Ker…
-
Why the model is not trained with the new batch at the line below?
https://github.com/ajsanjoaquin/Shapley_Valuation/blob/bf8cf85d3f8a288fdb43ca1c996be18dac25c56b/tmc.py#L154
-
When a reference portfolio algorithm is given, shouldn't we show the ERT loss ratio plots in the html pages? We could also show some Shapley values w.r.t. the reference algorithm set.
-
-
FedSHAP -- is there a paper for this code to read?