* add GCN sparse matrix example
* refine GCN example
* refine GCN example
* change train function
* [Bugfix] Turn off `use_alternate_stream` when TensorAdaptor is not enabled (#4987)
* turn off use_alternate_stream when tensoradaptor is not enabled
* add docstring
* Update (#4997)
Co-authored-by: Ubuntu <ubuntu@ip-172-31-36-188.ap-northeast-1.compute.internal>
* refine GCN example
* add GCN sparse matrix example
* refine GCN example
* refine GCN example
* change train function
* refine GCN example
* add highlight comment
* refine code
* refine code
* refine by black and flake8
* refine the comment to 80 char length
* refine the comment
* refine comment
Co-authored-by: Xin Yao <xiny@nvidia.com>
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-36-188.ap-northeast-1.compute.internal>
* Add GraphTransformerLayer (dense)
* beautify the python code with black
* refine according to mufei's comments
* fix AttributeError in unit test
* rename module as GraphormerLayer
* fix name issue
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
* update agg function with new bindings
* handle optional import in __init__
* raise error in RelGraphConvAgg when pylibcugraphops not imported
* Update tests/cugraph/cugraph-ops/test_cugraph_relgraphconv.py
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
* Update tests/cugraph/cugraph-ops/test_cugraph_relgraphconv.py
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
* use keyword args for readability
* add missing docstring to pass CI
* catch ImportError rather than ModuleNotFoundError
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
* Add support for next cusparse release
* Fix lint
* Add switch and tune the performance
* Fix lint issue
* Fine tune the heuristics
* Fix lint issue
* Address comments
* Minor fix
* Address comments
* Add PathEncoder to transformer.py
* add blank line at the and
* rename variabl sp to shortest_path
* Fixed corresponding problems
* Fixed certain bugs when running on CUDA
* changed clamp min from 0 to 1
Co-authored-by: Ubuntu <ubuntu@ip-172-31-14-146.ap-northeast-1.compute.internal>
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
Correction like mentioned in #4969
I noticed that there is a normalisation step on line 97 while the normalised values are not used downstream. Even if this was meant to show the normalisation step, it would not be calculating the normalisation step described in the CGN paper. The paper considers both in and out degrees while the normalisation in the code only describes normalisation using the in degrees.
In the end, the normalised values are assigned to g.ndata["norm"] but these values are not used afterwards.
Having a normalisation step here is also unnecessary since the GraphConv layer that is used already takes care of the normalisation. https://docs.dgl.ai/en/0.9.x/_modules/dgl/nn/pytorch/conv/graphconv.html#GraphConv
It confused me for a second thinking that I had to do the normalisation myself but this is already handled by the GraphConf.
* replace dgl PRNG with pcg32
* remove pcg submodule, add a simple implementation
* replace pcg32 with std::mt19937_64
* fix include order
* change RandomEngine to pcg32
* Remove custom pcg32 implementation, use the submodule provided by the original author.
* minor bug
* move include for linting
* include pcg for tests too
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
* Leverage hashmap to accelerate CSRSliceMatrix
* fix lint check
* use `min` in cuda_runtime.ch
* fix hash func
* add some comments and adjust the <grid,block> of the _SegmentMaskColKernel kernel
* set device and stream for thrust::for_each
* use thrust::cuda::par_nosync
Co-authored-by: Xin Yao <xiny@nvidia.com>
* adding LABOR sampling
* add ladies and pladies samplers
* fix compile error after rebase
* add reference for ladies sampler
* Improve ladies implementation.
* weighted labor sampling initial implementation draft
fix indentation and small bug in ladies script
* importance_sampling currently doesn't work with weights
* fix weighted importance sampling
* move labor example into its own folder
* lint fixes
* Improve documentation
* remove examples from the main PR
* fix linting by not using c++17 features
* fix documentation of labor_sampler.py
* update documentation for labor.py
* reformat the labor.py file with black
* fix linting errors
* replace exception use with if
* fix typo in error comment
* fixing win64 build for ci
* fixing weighted implementation, works now.
* fix bug in the weighted case and importance_sampling==0
* address part of the reviews
* remove unused code paths from cuda
* remove unused code path from cpu side
* remove extra features of labor making use of random seed.
* fix exclude_edges bug
* remove pcg and seed logic from cpu implementation, seed logic should still work for cuda.
* minor style change
* refactor CPU implementation, take out the importance_sampling probability computation into a function.
* improve CUDAWorkspaceAllocator
* refactor importance_sampling part out to a function
* minor optimization
* fix linting issue
* Revert "remove pcg and seed logic from cpu implementation, seed logic should still work for cuda."
This reverts commit c250e07ac6d7e13f57e79e8a2c2f098d777378c2.
* Revert "remove extra features of labor making use of random seed."
This reverts commit 7f99034353080308f4783f27d9a08bea343fb796.
* fix the documentation
* disable NIDs
* improve the documentation in the code
* use the stream argument in pcg32 instead of skipping ahead t times, can discard the use of hashmap now since it is faster this way.
* fix linting issue
* address another round of reviews
* further optimize CPU LABOR sampling implementation
* fix linting error
* update the comment
* reformat
* rename and rephrase comment
* fix formatting according to new linting specs
* fix compile error due to renaming, fix linting.
* lint
* rename DGLHeteroGraph to DGLGraph to match master
* replace other occurrences of DGLHeteroGraph to DGLGraph
Co-authored-by: Muhammed Fatih BALIN <m.f.balin@gmail.com>
Co-authored-by: Kaan Sancak <kaansnck@gmail.com>
Co-authored-by: Quan Gan <coin2028@hotmail.com>
* [Dist] instantiate NodeDataView in lazy mode
* fix test failure
* init node/edge data store at the very beginning
* fix test failures
* refine comment
* add more tests
* Update CUDA.cmake to align with PyTorch's
* add Ada and Hopper
* add more comments
* resolve comments
Co-authored-by: Triston <triston.cao@gmail.com>
* Flexible pipeline - Initial commit
1. Implementation of flexible pipeline feature.
2. With this implementation, the pipeline now supports multiple partitions per process. And also assumes that num_partitions is always a multiple of num_processes.
* Update test_dist_part.py
* Code changes to address review comments
* Code refactoring of exchange_features function into two functions for better readability
* Upadting test_dist_part to fix merge issues with the master branch
* corrected variable names...
* Fixed code refactoring issues.
* Provide missing function arguments to exchange_feature function
* Providing the missing function argument to fix error.
* Provide missing function argument to 'get_shuffle_nids' function.
* Repositioned a variable within its scope.
* Removed tab space which is causing the indentation problem
* Fix issue with the CI test framework, which is the root cause for the failure of the CI tests.
1. Now we read files specific to the partition-id and store this data separately, identified by the local_part_id, in the local process.
2. Similarly as above, we also differentiate the node and edge features type_ids with the same keys as above.
3. These above two changes will help up to get the appropriate feature data during the feature exchange and send to the destination process correctly.
* Correct the parametrization for the CI unit test cases.
* Addressing Rui's code review comments.
* Addressing code review comments.
Xin Yao