[BUG] Better warning / assert and handling of cases where CAGRA graph degree is not strictly larger than intermediate graph degree.
Nobody has claimed this yet.
- Dominant language
- Cuda
- Stars
- 854
- Forks
- 236
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 62
Description
Currently, CAGRA does an assertion that graph degree is not less than intermediate graph degree, but even if graph degree is too close to intermediate graph degree, it's possible there's not enough neighborhood information encoded in the intermediate knn graph for the pruning to have a connected graph.
When this case happens, the user gets an error that's nebulus and doesn't provide enough information for the user to
- know what happened, and
- fix the issue.
In general, users aren't going to know the complex relationships between parameters like this, but we often make a suggestion that intermediate graph degree by 1.5 * graph degree.
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 by locating the CAGRA graph-degree assertion and the code that reports the pruning or connectivity failure. Reproduce a case where the graph degree is only slightly larger than the intermediate graph degree, then make the warning explain the parameter relationship and suggested ratio; done means users can identify and correct the invalid configuration.
Written by the indexing model from the issue text.
Assessment
- Domain
- search
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100