SparseTensor support for trim_to_layer#7089
Conversation
…o considered). sage works on ogbn-products; gcn not yet
In the case of gcn data does not come always with rowptr/csr layout information in adj_t
Related tests are included. It provides significant speed up for CPU workloads on homogenous graphs
for more information, see https://pre-commit.ci
Codecov Report
@@ Coverage Diff @@
## master #7089 +/- ##
==========================================
- Coverage 91.72% 91.26% -0.47%
==========================================
Files 437 436 -1
Lines 23983 23949 -34
==========================================
- Hits 21999 21857 -142
- Misses 1984 2092 +108
... and 30 files with indirect coverage changes 📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
|
@rusty1s To my understanding, that absence generates issues with this contribution in a number of tests:
the only one not impacted by the absence of torch_sparse is the changelog failure, which was however present also in other PRs recently merged... so I guess that should not be blocking for now. How would you like me to go on? |
|
You need to import from |
Sure, it clarifies, thanks! |
for environments without torch_sparse, which is no longer a dependency of PyG
…azanetti/pytorch_geometric into trim_to_layer_SparseTensor
for more information, see https://pre-commit.ci
…azanetti/pytorch_geometric into trim_to_layer_SparseTensor
for more information, see https://pre-commit.ci
https://github.com/andreazanetti/pytorch_geometric into trim_to_layer_SparseTensor Corrected CHANGELOG.md
SparseTensor support for trim_to_layer
It provides support for SparseTensor data format for the trim_to_layer.py functionality.
The trimming function is isolated in a separate function, but still contained in trim_to_layer.py, as it is useful to that only.
Tests are included extending the test file used for trim_to_layer.py.
Some tests already present in a previous PR were slightly modified as to simulate a adj_t matrix that originates from a BFS traversal of a graph, starting the BFS traversal from the target node (assuming Batch Size = 1)