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.

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

Optimize LightGCN Model #531

Merged
merged 25 commits into from
Oct 17, 2023
Merged

Conversation

darrylong
Copy link
Member

Description

Optimizing LightGCN model to make it consistent with NGCF model.

Related Issues

Checklist:

  • I have added tests.
  • I have updated the documentation accordingly.
  • I have updated README.md (if you are adding a new model).
  • I have updated examples/README.md (if you are adding a new example).
  • I have updated datasets/README.md (if you are adding a new dataset).

@darrylong darrylong requested a review from tqtg October 13, 2023 03:58
@darrylong darrylong self-assigned this Oct 13, 2023
cornac/models/lightgcn2/lightgcn.py Outdated Show resolved Hide resolved
cornac/models/lightgcn2/recom_lightgcn.py Outdated Show resolved Hide resolved
cornac/models/lightgcn2/recom_lightgcn.py Outdated Show resolved Hide resolved
examples/lightgcn_example.py Outdated Show resolved Hide resolved
@tqtg
Copy link
Member

tqtg commented Oct 16, 2023

@darrylong shall we try to clean up this PR and merge it?

@tqtg tqtg marked this pull request as ready for review October 17, 2023 04:27
@tqtg
Copy link
Member

tqtg commented Oct 17, 2023

LGTM

@darrylong darrylong merged commit a470d5c into PreferredAI:master Oct 17, 2023
12 checks passed
@darrylong darrylong deleted the improve-lightgcn branch October 17, 2023 05:53
darrylong added a commit to darrylong/cornac that referenced this pull request Oct 23, 2023
* Generated model base from LightGCN

* wip

* wip example

* add self-connection

* refactor code

* added sanity check

* Changed train batch size in example to 1024

* Updated readme for example folder

* Update Readme

* update docs

* Update block comment

* WIP

* Updated validation metric

* Updated message handling

* Added legacy lightgcn for comparison purposes

* Changed to follow 'a_k = 1/(k+1)',  k instead of i

* Changed early stopping technique to follow NGCF

* remove test_batchsize, early stop verbose to false

* Changed parameters to align with paper and ngcf

* refractor codes

* update docstring

* change param name to 'batch_size'

* Fix paper reference

---------

Co-authored-by: tqtg <tuantq.vnu@gmail.com>
Co-authored-by: Quoc-Tuan Truong <tqtg@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants