-
This issue is devoted to the discussion of lifted operators: both their design and implementation details, as well as the grounding philosophy that ought to inform our treatment of them in this packag…
-
Hi all,
I'm trying to use Anchor Tabular on a new model, but I cannot fit the anchor. The model works with missing data so initially I've been using missing data to train the explainer. I've also …
-
Comment below with questions or thoughts about the reading for this week's workshop.
Please make your comments by Wednesday 11:59 PM, and upvote at least five of your peers' comments on Thursday pr…
-
In this example I intend to show how we should use multiple dispatch as a base for the entire generation of counterfactual explanations. Idea is that _every_ step is customizable. Here, I use the simp…
-
Obviously, there's only so much we can do, but we can do some. The most obvious optimization is to use a version of `insertMin` that takes a singleton tree as an argument instead of an element. But I …
-
**Describe the bug**
When running the Mondrian_Fairness.ipynb, several counterfactual plots repeat the same alternative rule multiple times.
**To Reproduce**
Steps to reproduce the behavior:
Ru…
-
Hello,
I am doing multivariate time series classification with 2 features.
I am trying to use COMTE explain function.
However I am facing issues where the returned label of the explain function…
-
**Submitting author:** @BirkhoffG (Hangzhi Guo)
**Repository:** https://github.com/BirkhoffG/jax-relax/
**Branch with paper.md** (empty if default branch): joss
**Version:** v0.2.4
**Editor:** @Fei-Ta…
-
**1. Nearest Neighbours**
From what I understand the algorithm always finds the nearest neighbour of opposite class in the training data.
This makes the counterfactuals always deterministic an…
-
**Submitting author:** @pat-alt (Patrick Altmeyer)
**Repository:** https://github.com/pat-alt/CounterfactualExplanations.jl
**Branch with paper.md** (empty if default branch):
**Version:** v0.1.14
**…