Founding Engineer
Creator of PyG (PyTorch Geometric) - Founding Engineer @ kumo.ai - PhD from TU Dortmund University - Interested in Graph Representation Learning
- Dortmund, Germany
- https://rusty1s.github.io
- @rusty1s
Highlights
- Pro
Block or Report
Block or report rusty1s
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
-
snap-stanford/ogb Public
Benchmark datasets, data loaders, and evaluators for graph machine learning
-
-
pytorch_sparse Public
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
-
pyg_autoscale Public
Implementation of "GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings" in PyTorch
-
Implementation of "Deep Graph Matching Consensus" in PyTorch
5,066 contributions in the last year
Less
More
Activity overview
Contributed to
pyg-team/pytorch_geometric,
pyg-team/pyg-lib,
rusty1s/pytorch_sparse
and 14 other
repositories
Contribution activity
June 2023
Created 52 commits in 3 repositories
Created a pull request in pyg-team/pytorch_geometric that received 1 comment
Opened 20 other pull requests in 2 repositories
pyg-team/pytorch_geometric
19
merged
-
Check lazy initialization with
SAGEConv(project=True) -
Allow GPU input in
NodeLoaderandLinkLoader -
Move
ConfigStoreoutside GraphGym repository -
Temporarily disable
pyg-lib+METIS tests -
Fix
get_mesh_laplacianwithnormalization="sym" -
Testing PyG with minimal dependencies (only
pyg-lib) -
Ensure same dtypes in
Planetoidprocessing -
Fix type hints in
InMemoryDataset -
Fix
NeighborLoadertests in casetorch-sparseis not installed -
Fix empty edge indices handling with
SparseTensor - Disable graph break test
-
Add number of sampled nodes/edges information to
LinkLoader -
Added the
HMpersonalized fashion recommendation dataset -
Fail gracefully in case
GNNExplainerwill not compute gradients for node features or edges -
Fix
GCN2example fortorch.sparse_csrlayout - Remove some warnings
-
Fix
disable_dynamic_shapesdecorator in combination with TorchScript - Fix full tests on master
-
cudfsupport inmap_index
rusty1s/pytorch_sparse
1
merged
Reviewed 44 pull requests in 6 repositories
pyg-team/pytorch_geometric
25 pull requests
- Add partitioning for distributed training
- Implementation of Directed Graph Neural Networks (Dir-GNN)
-
Added
edge_indexproperty toTemporalData -
feat(docker): bump version in
Dockerfile - Correctly move data to device in GraphSAGE example
-
adding backwards to
dense_diff_poolbenchmark -
Add an example
PMLPon Cora dataset -
Allow GPU inference in
BasicGNN -
topkbenchmark -
dense_diff_poolbenchmark -
Add a
num_nodesparameter to theHypergraphConvlayer -
Add
dim sizeparameter to theEquilibriumAggregationlayer potential function -
Add
LocalFeatureStoreandLocalGraphStorehelper initializations - Implementing Neural Fingerprint from Duvenaud et al.
-
Remove python fallbacks in
voxel_grid -
Use
repeatinstead ofnew_fullto avoid graph breaks into_dense_batch -
Add
max_num_nodesparameter to the constructor ofEquilibriumAggregationlayer -
Add usage of
disable_dynamic_shapedecorator in aggregation layers -
Fix for
NeighborSamplerformag240m -
Ensure data is on the same device in
knn_graph -
Add
max_num_elementsparameter to the forward method of aggregation layers -
Enable
trim_to_layerwith hetero CSR flow -
Add
NodeEncoderfrom the GraphMixer paper - Fix typo in documentation
-
Introduce
disable_dynamic_shapesexperimental flag; adding its use intoto_dense_batch function - Some pull request reviews not shown.
rusty1s/pytorch_scatter
2 pull requests
snap-stanford/ogb
1 pull request
pyg-team/pyg-lib
1 pull request
rusty1s/pytorch_sparse
1 pull request
pytorch/pytorch
1 pull request
Answered 6 discussions in 1 repository
pyg-team/pytorch_geometric
pyg-team/pytorch_geometric
-
Direct Message Passing along Edges
This contribution was made on Jun 17
-
LinkNeighborLoader error in cuda
This contribution was made on Jun 15
-
Question about Sampling Multiple Edge Types Simultaneously in Heterogeneous Graphs using PyG
This contribution was made on Jun 12
-
Graphgym config cfg.train.auto_resume not working?
This contribution was made on Jun 9
-
Creating an InMemoryDataset with HeteroData
This contribution was made on Jun 6
-
DataLoader shuffle affects loss and accuracy on evaluation
This contribution was made on Jun 1
94
contributions
in private repositories
Jun 1 – Jun 16






