Possible to backprop through UMAP encoding/sensitivity analysis?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.3k
- Forks
- 871
- Avg merge
- 1d 13h
- Merged PRs (30d)
- 5
Description
Hi,
If I constructed a pipeline consisting first of a UMAP embedding R^N->R^M followed by some differentiable mapping R^M->R1 (say, in the case of a simple binary classifier), is there a way to backprop 'through' the encoder such that one could perform something like integrated gradients for sensitivity analysis/feature attribution?
I'm very curious as to what people are doing for explainability when using UMAP. Of course it is always possible to do some sort of perturbation sensitivity analysis or kernelSHAP (etc), but this tends to not be super computationally efficient.
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
No files, tests, or entry points are named. Investigate how UMAP encoding is implemented and whether the requested backpropagation and integrated-gradients workflow fits the project; done would require a settled, documented approach or a clearly scoped implementation plan.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100