Cleanup examples #10097

xnuohz · 2025-03-05T12:51:05Z

Combine 15 examples related to cora into 1 file
Update related docs, github workflow, readme

for more information, see https://pre-commit.ci

puririshi98

code changes look good at first review, but for such an extensive change i would ask that you run every one of the deleted examples, and then the new version with its corresponding args for this planetoid example. I would ask that you share those logs and also check yourself to make sure that the new version is as good or better in terms of accuracy, speed, and readability. and if not for any reason try to understand why. This is a very valuable PR but we want to be careful with something like this.

If compute is an issue, i would ask that you write a bash script for me that will automatically run the above experiments and have the logs saved to some shared cloud drive or a github repo so you can do the above mentioned anlaysis after i run the script.

regardless once you have said analysis, i will look through myself as well and make sure our analyses align. then i think this is safe to merge

puririshi98 · 2025-03-06T17:54:52Z

also please update the changelog

akihironitta

Looks great so far! ✨

Tbh, I'd vote for having many separate 90~100 lines of code examples to allow users to immediately understand what the script does and easily modify the scirpt that they're interested in (at the cost of maintaining duplicate code in the example directory), but I guess this is just my preference.

Could we also add type annotations?

akihironitta · 2025-03-07T22:55:42Z

examples/planetoid_train.py

+if not WITH_TORCH_SPLINE_CONV:
+    quit("This example requires 'torch-spline-conv'")


Does this script need the package in all cases?

updated and only judged when gnn_choice = splinegnn

examples/planetoid_train.py

for more information, see https://pre-commit.ci

…c into examples/cleanup

examples/README.md

examples/planetoid_train.sh

examples/run_cora.sh

examples/planetoid_train.py

puririshi98 · 2025-03-17T21:36:39Z

@xnuohz please put all of the planetoid examples back and make the readme explain how they are all repro'd by the single planetoid_train.py if people want a unified and extendable framework. mention the originals are for individual examples and learning.

for more information, see https://pre-commit.ci

codecov · 2025-03-22T01:10:58Z

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 85.43%. Comparing base (c211214) to head (aba6642).
Report is 29 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master   #10097      +/-   ##
==========================================
- Coverage   86.11%   85.43%   -0.68%     
==========================================
  Files         496      496              
  Lines       33655    34001     +346     
==========================================
+ Hits        28981    29049      +68     
- Misses       4674     4952     +278

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

puririshi98

this LGTM once you address my one comment, but curious what @akihironitta thinks now. from our PoV in the longrun it is good to have unified code snippets for testing and customer use. the new planetoid_train.py offers that while explaining what old examples it combines

puririshi98 · 2025-03-26T15:58:05Z

README.md

- **[GATConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.GATConv.html)** from Veličković *et al.*: [Graph Attention Networks](https://arxiv.org/abs/1710.10903) (ICLR 2018) \[[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/gat.py)\]
+- **[GCNConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.GCNConv.html)** from Kipf and Welling: [Semi-Supervised Classification with Graph Convolutional Networks](https://arxiv.org/abs/1609.02907) (ICLR 2017) \[[**Example1**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/gcn.py), [**Example2**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/planetoid_train.py)\]
+- **[ChebConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.ChebConv.html)** from Defferrard *et al.*: [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://arxiv.org/abs/1606.09375) (NIPS 2016) \[[**Example1**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/gcn.py#L36-L37), [**Example2**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/planetoid_train.py#L115-L116)\]
+- **[GATConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.GATConv.html)** from Veličković *et al.*: [Graph Attention Networks](https://arxiv.org/abs/1710.10903) (ICLR 2018) \[[**Example1**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/gat.py), [**Example2**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/planetoid_train.py)\]


rather than showing planetoid_train in all these duplicate places, please explain that "planetoid_train.py offers a unified codebase covering GCN, GAT, and Cheb Convs, as well as many more"

puririshi98

i see you swapped example -> example1 in severl places, can you explain why?

puririshi98 · 2025-05-01T15:56:37Z

README.md

 - **[PNAConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.PNAConv.html)** from Corso *et al.*: [Principal Neighbourhood Aggregation for Graph Nets](https://arxiv.org/abs/2004.05718) (CoRR 2020) \[**[Example](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/pna.py)**\]
 - **[FAConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.FAConv.html)** from Bo *et al.*: [Beyond Low-Frequency Information in Graph Convolutional Networks](https://arxiv.org/abs/2101.00797) (AAAI 2021)
 - **[PDNConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.nn.conv.PDNConv.html)** from Rozemberczki *et al.*: [Pathfinder Discovery Networks for Neural Message Passing](https://arxiv.org/abs/2010.12878) (WWW 2021)
 - **[RGCNConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.RGCNConv.html)** from Schlichtkrull *et al.*: [Modeling Relational Data with Graph Convolutional Networks](https://arxiv.org/abs/1703.06103) (ESWC 2018) \[[**Example1**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/rgcn.py), [**Example2**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/rgcn_link_pred.py)\]
 - **[RGATConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.RGATConv.html)** from Busbridge *et al.*: [Relational Graph Attention Networks](https://arxiv.org/abs/1904.05811) (CoRR 2019) \[[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/rgat.py)\]
 - **[FiLMConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.FiLMConv.html)** from Brockschmidt: [GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation](https://arxiv.org/abs/1906.12192) (ICML 2020) \[[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/film.py)\]
 - **[SignedConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.SignedConv.html)** from Derr *et al.*: [Signed Graph Convolutional Network](https://arxiv.org/abs/1808.06354) (ICDM 2018) \[[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/signed_gcn.py)\]
- **[DNAConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.DNAConv.html)** from Fey: [Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks](https://arxiv.org/abs/1904.04849) (ICLR-W 2019) \[[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/dna.py)\]
+- **[DNAConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.DNAConv.html)** from Fey: [Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks](https://arxiv.org/abs/1904.04849) (ICLR-W 2019) \[[**Example1**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/dna.py)\]


why did you switch example -> example1 here? @xnuohz

last time when i deleted the separate examples and updated the readme, forgot to change it back. should be fine now

puririshi98 · 2025-05-01T15:56:52Z

README.md

- **[AGNNConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.AGNNConv.html)** from Thekumparampil *et al.*: [Attention-based Graph Neural Network for Semi-Supervised Learning](https://arxiv.org/abs/1803.03735) (CoRR 2017) \[[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/agnn.py)\]
- **[TAGConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.TAGConv.html)** from Du *et al.*: [Topology Adaptive Graph Convolutional Networks](https://arxiv.org/abs/1710.10370) (CoRR 2017) \[[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/tagcn.py)\]
+- **[AGNNConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.AGNNConv.html)** from Thekumparampil *et al.*: [Attention-based Graph Neural Network for Semi-Supervised Learning](https://arxiv.org/abs/1803.03735) (CoRR 2017) \[[**Example1**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/agnn.py)\]
+- **[TAGConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.TAGConv.html)** from Du *et al.*: [Topology Adaptive Graph Convolutional Networks](https://arxiv.org/abs/1710.10370) (CoRR 2017) \[[**Example1**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/tagcn.py)\]


same thing here

puririshi98

LGTM, just ask that @akihironitta give a final stamp of approval

xnuohz added 10 commits March 1, 2025 16:29

cleanup 9 gnn models on cora dataset

5e73c3c

dna, super_gat

81ee836

gat, gcn

7540ad8

node2vec

4ac9df4

align with ogbn train

29b6766

update readme

9742f25

update

1a8909e

Merge branch 'master' into examples/cleanup

cb944ba

update

b47cf2d

update

a122eb5

xnuohz requested review from a team, wsad1, rusty1s and EdisonLeeeee as code owners March 5, 2025 12:51

pre-commit-ci bot and others added 2 commits March 5, 2025 12:53

[pre-commit.ci] auto fixes from pre-commit.com hooks

765d296

for more information, see https://pre-commit.ci

Merge branch 'master' into examples/cleanup

ad43f2c

puririshi98 requested changes Mar 6, 2025

View reviewed changes

add readme

f3962c4

akihironitta reviewed Mar 7, 2025

View reviewed changes

akihironitta added refactor example labels Mar 7, 2025

xnuohz and others added 8 commits March 8, 2025 17:18

add type hints

6c10b3b

[pre-commit.ci] auto fixes from pre-commit.com hooks

1497633

for more information, see https://pre-commit.ci

update

768b257

Merge branch 'examples/cleanup' of github.com:xnuohz/pytorch_geometri…

47cd6f4

…c into examples/cleanup

update

01ebfc0

update

a96ec03

update

abe9260

update

f8113a3

xnuohz commented Mar 14, 2025

View reviewed changes

examples/README.md Outdated Show resolved Hide resolved

examples/planetoid_train.sh Outdated Show resolved Hide resolved

examples/run_cora.sh Outdated Show resolved Hide resolved

examples/planetoid_train.py Outdated Show resolved Hide resolved

xnuohz added 3 commits March 16, 2025 02:34

delete useless files and update changelog

9bdfc6e

fix broken tj-action/changed-files

a941d82

update readme

c29ffbd

xnuohz and others added 8 commits March 18, 2025 20:09

restore

6b287d7

[pre-commit.ci] auto fixes from pre-commit.com hooks

3074d70

for more information, see https://pre-commit.ci

Restore individual examples (#2)

a5945f7

update

73a6380

update

7d9ba54

Merge branch 'master' into examples/cleanup

c445ffb

Merge branch 'master' into examples/cleanup

44293f9

update

d829ec6

puririshi98 and others added 2 commits March 26, 2025 08:31

Merge branch 'master' into examples/cleanup

242fa69

Update README.md

6f4d0ab

puririshi98 requested changes Mar 26, 2025

View reviewed changes

xnuohz mentioned this pull request Mar 27, 2025

pytorch_geometric is using a compromised tj-actions/changed-files GitHub action #10119

Closed

xnuohz and others added 6 commits March 27, 2025 18:33

update

84b1d26

Merge branch 'master' into examples/cleanup

e2d2ff6

Merge branch 'master' into examples/cleanup

09d4f62

Merge branch 'master' into examples/cleanup

48d29cb

Merge branch 'master' into examples/cleanup

219eece

Merge branch 'master' into examples/cleanup

cc2d718

puririshi98 requested changes May 1, 2025

View reviewed changes

puririshi98 and others added 4 commits May 1, 2025 08:57

Merge branch 'master' into examples/cleanup

a60007e

update

976cd71

update

0e7430a

Merge branch 'master' into examples/cleanup

aba6642

puririshi98 requested changes May 6, 2025

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Cleanup examples #10097

Cleanup examples #10097

xnuohz commented Mar 5, 2025

puririshi98 left a comment

puririshi98 commented Mar 6, 2025

akihironitta left a comment

akihironitta Mar 7, 2025

xnuohz Mar 8, 2025

puririshi98 commented Mar 17, 2025

codecov bot commented Mar 22, 2025 •

edited

Loading

puririshi98 left a comment

puririshi98 Mar 26, 2025

puririshi98 left a comment

puririshi98 May 1, 2025

xnuohz May 1, 2025

puririshi98 May 1, 2025

puririshi98 left a comment

		if not WITH_TORCH_SPLINE_CONV:
		quit("This example requires 'torch-spline-conv'")

Cleanup examples #10097

Are you sure you want to change the base?

Cleanup examples #10097

Conversation

xnuohz commented Mar 5, 2025

puririshi98 left a comment

Choose a reason for hiding this comment

puririshi98 commented Mar 6, 2025

akihironitta left a comment

Choose a reason for hiding this comment

akihironitta Mar 7, 2025

Choose a reason for hiding this comment

xnuohz Mar 8, 2025

Choose a reason for hiding this comment

puririshi98 commented Mar 17, 2025

codecov bot commented Mar 22, 2025 • edited Loading

Codecov Report

puririshi98 left a comment

Choose a reason for hiding this comment

puririshi98 Mar 26, 2025

Choose a reason for hiding this comment

puririshi98 left a comment

Choose a reason for hiding this comment

puririshi98 May 1, 2025

Choose a reason for hiding this comment

xnuohz May 1, 2025

Choose a reason for hiding this comment

puririshi98 May 1, 2025

Choose a reason for hiding this comment

puririshi98 left a comment

Choose a reason for hiding this comment

codecov bot commented Mar 22, 2025 •

edited

Loading