-
Notifications
You must be signed in to change notification settings - Fork 506
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.
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
Implementation of Low Rank Gromov-Wasserstein #614
Conversation
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #614 +/- ##
========================================
Coverage 96.77% 96.78%
========================================
Files 81 83 +2
Lines 16106 16284 +178
========================================
+ Hits 15587 15760 +173
- Misses 519 524 +5 |
Hello @laudavid, Best, |
Hello Cédric, Have a nice day, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you again for this nice PR :)
Here are some remarks to complete your work and clarify few elements.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for these updates :) The PR is ready imo, we recently fixed POT testing mechanism. Could you pull the last version of the master branch so that we can proceed with the merge ?
Types of changes
This PR is for the implementation of the Low Rank Gromov-Wasserstein solver.
Paper reference:
Scetbon, M., Peyré, G. & Cuturi, M. (2022).
"Linear-Time GromovWasserstein Distances using Low Rank Couplings and Costs".
In International Conference on Machine Learning (ICML), 2022.
Changes made:
lowrank_gromov_wasserstein
function inot/lowrank.py
_flat_product_operator
function inot/lowrank.py
since it is needed for the low rank GW solvertest\lowrank.py
lowrank_gromov_wasserstein
solver in__init__.py
READ.me
plot_lowrank_GW.py
) inexamples/others
Motivation and context / Related issue
Adding a new low rank solver for gromov-wasserstein.
No existing issue is linked to this PR.
How has this been tested (if it applies)
Tests for each function are available in
test_lowrank.py
.The Low Rank GW solver has also been tested by reproducing Figure 2 from the paper.
PR checklist