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

[Example] fixing TGN example #6619

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Conversation

amarzullo24
Copy link

@amarzullo24 amarzullo24 commented Nov 26, 2023

Description

Attempt to fix the example: Temporal Graph Network (TGN)
refer to #5452 #3536 #5456

Checklist

Please feel free to remove inapplicable items for your PR.

  • The PR title starts with [$CATEGORY] (such as [NN], [Model], [Doc], [Feature]])
  • I've leverage the tools to beautify the python and c++ code.
  • The PR is complete and small, read the Google eng practice (CL equals to PR) to understand more about small PR. In DGL, we consider PRs with less than 200 lines of core code change are small (example, test and documentation could be exempted).
  • All changes have test coverage
  • Code is well-documented
  • To the best of my knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change
  • Related issue is referred in this PR
  • If the PR is for a new model/paper, I've updated the example index here.

Changes

TGN example was removed due to compatibility issues with recent DGL versions (https://github.com/dmlc/dgl/blob/master/examples/pytorch/tgn)
This PR contains simple fixes to adapt the dataloader

Tested by running in fast mode:

python train.py --dataset wikipedia --fast_mode

Obtained performance is comparable with the one reported in the previous version:

Batch:  462 Time:  0.11104059219360352
Batch:  463 Time:  0.13099265098571777
Batch:  464 Time:  0.11907100677490234
Batch:  465 Time:  0.11619687080383301
Batch:  466 Time:  0.11682605743408203
Batch:  467 Time:  0.12520647048950195
Batch:  468 Time:  0.10740518569946289
Batch:  469 Time:  0.11810636520385742
Batch:  470 Time:  0.033731937408447266
Epoch: 49; Training Loss: 28394.831434637308 | Validation AP: 0.985 AUC: 0.987
 Epoch: 49; Test AP: 0.983 AUC: 0.987
 Epoch: 49; Test New Node AP: 0.980 AUC: 0.983

========Training is Done========

@dgl-bot
Copy link
Collaborator

dgl-bot commented Nov 26, 2023

Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:

  • @dgl-bot

@dgl-bot
Copy link
Collaborator

dgl-bot commented Nov 26, 2023

Commit ID: c64592b86240826625ae1080a57fe69be280aed8

Build ID: 1

Status: ❌ CI test failed in Stage [Authentication].

Report path: link

Full logs path: link

@BarclayII BarclayII self-requested a review November 30, 2023 02:21
@dgl-bot
Copy link
Collaborator

dgl-bot commented Nov 30, 2023

Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:

  • @dgl-bot

@dgl-bot
Copy link
Collaborator

dgl-bot commented Nov 30, 2023

Commit ID: 538386b

Build ID: 2

Status: ❌ CI test failed in Stage [Authentication].

Report path: link

Full logs path: link

@dgl-bot
Copy link
Collaborator

dgl-bot commented Dec 4, 2023

Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:

  • @dgl-bot

@dgl-bot
Copy link
Collaborator

dgl-bot commented Dec 4, 2023

Commit ID: a60aa22

Build ID: 3

Status: ❌ CI test failed in Stage [Authentication].

Report path: link

Full logs path: link

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.

None yet

2 participants