Skip to content

[Feature] HGAM hetero low-level example #7425

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
Merged
rusty1s merged 12 commits into from
May 27, 2023
Merged

[Feature] HGAM hetero low-level example #7425

rusty1s merged 12 commits into from
May 27, 2023

Conversation

@mszarma
Copy link
Contributor

@mszarma mszarma commented May 24, 2023

  • enable hetero part for CSR in trim_to_layer
  • refactor of trim_to_layer utils to add low-level functions
  • add hgam hetero low-level example

@mszarma mszarma requested review from andreazanetti and rusty1s May 24, 2023 11:47
@codecov
Copy link

codecov bot commented May 24, 2023 •
edited
Loading

Codecov Report

Merging #7425 (d28d2c0) into master (d64fa43) will decrease coverage by 0.01%.
The diff coverage is 88.88%.

❗ Current head d28d2c0 differs from pull request most recent head 7e809ab. Consider uploading reports for the commit 7e809ab to get more accurate results

@@            Coverage Diff             @@
##           master    #7425      +/-   ##
==========================================
- Coverage   91.43%   91.43%   -0.01%     
==========================================
  Files         445      445              
  Lines       24689    24696       +7     
==========================================
+ Hits        22575    22580       +5     
- Misses       2114     2116       +2
Impacted Files Coverage Δ
torch_geometric/utils/trim_to_layer.py 94.23% <88.88%> (-3.55%) ⬇️

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

@mszarma mszarma force-pushed the hgam_hetero_low_level_example branch 2 times, most recently from e0306ca to fb3bf7a Compare May 24, 2023 12:07
@mszarma
Adding:
cbdaba9 
- refactor of trim_to_layer utils to add low-level functions
- add hgam hetero low-level example
@mszarma mszarma force-pushed the hgam_hetero_low_level_example branch from fb3bf7a to cbdaba9 Compare May 24, 2023 12:08
@rusty1s rusty1s marked this pull request as ready for review May 27, 2023 20:55
@rusty1s rusty1s requested a review from wsad1 as a code owner May 27, 2023 20:55
rusty1s
rusty1s approved these changes May 27, 2023
View reviewed changes
Copy link
Member

@rusty1s rusty1s left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you @mszarma. Can we add bipartite SparseTensor support in a follow-up?

@rusty1s rusty1s enabled auto-merge (squash) May 27, 2023 21:01
@rusty1s rusty1s merged commit d8a651c into pyg-team:master May 27, 2023
@mszarma
Copy link
Contributor Author

mszarma commented Jun 5, 2023

Thank you @mszarma. Can we add bipartite SparseTensor support in a follow-up?
Opened PR in that topic:
https://github.com/pyg-team/pytorch_geometric/pull/7514/files

@mszarma mszarma mentioned this pull request Jun 5, 2023
Merged
rusty1s added a commit that referenced this pull request Jun 5, 2023
@mszarma @rusty1s
Enable trim_to_layer with hetero CSR flow (#7514)
89e781d 
Enable
https://github.com/pyg-team/pytorch_geometric/blob/master/examples/hetero/hierarchical_sage.py
using SparseTensor flow
(#7425 (review))

---------

Co-authored-by: rusty1s <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@rusty1s rusty1s rusty1s approved these changes

@andreazanetti andreazanetti Awaiting requested review from andreazanetti

@wsad1 wsad1 Awaiting requested review from wsad1 wsad1 is a code owner

Assignees

@mszarma mszarma

Labels

1 - Priority P1 example feature

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@mszarma @rusty1s