-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
joss paper #34
base: master
Are you sure you want to change the base?
joss paper #34
Conversation
Recourse and counterfactual explanation methods concentrate on the generation of new instances that lead to contrastive predicted outcomes [@verma2020counterfactual;@karimi2020survey;@stepin2021survey]. Given their ability to provide actionable recourse, these explanations are often favored by human end-users [@binns2018s;@miller2019explanation;@Bhatt20explainable]. | ||
|
||
|
||
Despite progress made in counterfactual explanation research [@wachter2017counterfactual;@mothilal2020explaining;@ustun2019actionable;@upadhyay2021towards;@vo2023feature;@guo2021counternet;@guo2023rocoursenet], current research practices often restrict the evaluation of recourse explanation methods on medium-sized datasets (with under 50k data points). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Start with many of these methods are slow
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I am going to leave this paragraph as-is because it is more about the slowness of implementation in those libraries. It is not because these methods are slow. It is mostly because they are implemented inefficiently.
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
Made stylistic edits.
No description provided.