Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Approximate nearest neighbour for BPR/LMF and GPU models #487

Closed
Tracked by #481
benfred opened this issue Nov 1, 2021 · 1 comment · Fixed by #502
Closed
Tracked by #481

Approximate nearest neighbour for BPR/LMF and GPU models #487

benfred opened this issue Nov 1, 2021 · 1 comment · Fixed by #502

Comments

@benfred
Copy link
Owner

benfred commented Nov 1, 2021 •
edited
Loading

Approximate nearest neighbours only works for the ALS model - and not on BPR or LMF. Likewise this doesn't work on the GPU models. We should change the ANN models to be composable - and wrap any other MF model
@benfred benfred mentioned this issue Nov 1, 2021
Closed
6 tasks
@benfred benfred changed the title Approximate nearest neighbours only works for the ALS model - and not on BPR or LMF. Likewise this doesn't work on the GPU models. We should change the ANN models to be composable - and wrap any other MF model Approximate nearest neighbour for BPR/LMF and GPU models Nov 2, 2021
@benfred benfred closed this as completed Nov 8, 2021
@benfred benfred reopened this Nov 8, 2021
benfred added a commit that referenced this issue Dec 31, 2021
@benfred
Make approximate nearest neighbours models composable.
ae53695 
Approximate nearest neighbours used to only work for the ALS mode on the CPU.

This change makes it so that we can compose ANN methods with any matrix factorization
model (including BPR/LMF) and also use the GPU MF models as well.

Currently this provides the same api in implicit/approximate_als.py for backwards
compatability - but this may be removed at a future date.

Closes #487
@benfred benfred mentioned this issue Dec 31, 2021
Merged
benfred added a commit that referenced this issue Dec 31, 2021
@benfred
Approximate nearest neighbour for BPR/LMF and GPU models (#502)
fb11321 
Approximate nearest neighbours used to only work for the ALS mode on the CPU.

This change makes it so that we can compose ANN methods with any matrix factorization
model (including BPR/LMF) and also use the GPU MF models as well.

Currently this provides the same api in implicit/approximate_als.py for backwards
compatibility - but this may be removed at a future date.

Closes #487
@benfred benfred linked a pull request Jan 3, 2022 that will close this issue
Make approximate nearest neighbours models composable. #502
Merged
@benfred
Copy link
Owner Author

benfred commented Jan 3, 2022

done in #502

@benfred benfred closed this as completed Jan 3, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Make approximate nearest neighbours models composable. benfred/implicit
1 participant
@benfred