Trusted-AI / Trusted-AI/AIX360
CEM for Multi-label Classification
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.8k
- Forks
- 327
- Avg merge
- 1h 13m
- Merged PRs (30d)
- 1
Description
Inspecting the KerasClassifier class for CEM, I could see that it is made specifically for single label classification:
predicted_class = np.argmax(prob)
It may be important to prepare this class to handle Multi Label Multi Class classification, maybe allowing the programmer to select which of the N target classes to take into account when explaining with CEMExplainer.
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
Start with aix360/algorithms/contrastive/classifiers.py, especially KerasClassifier around the referenced prediction logic, then trace how CEMExplainer uses it. Determine the expected behavior for multi-label, multi-class models and how a target class is selected. Done means CEM can explain a chosen target class without assuming single-label output, with suitable coverage in the existing test structure if one is found.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- keras, python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100