Trusted-AI / Trusted-AI/AIX360
How to evaluate shap local explanations with Faithfulness and monotoncity metrics?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.8k
- Forks
- 327
- Avg merge
- 1h 13m
- Merged PRs (30d)
- 1
Description
Hello,
I want to evaluate the SHAP local explanations with Faithfulness and monotonicity metrics along LIME explainer. Should we have to use shap values in place of lime coefficients to evaluate the SHAP local explanations? Thank you.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue mentions SHAP, LIME, Faithfulness, and monotonicity metrics but names no files, tests, or entry points. First locate the existing local-explanation evaluation code and determine how SHAP explanations are represented alongside LIME. Done means the project has a clear, agreed answer about evaluating SHAP explanations with these metrics.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100