7c7113f660
add use_ddp to dataloaders ( #2911 )
2021-05-17 15:46:02 +08:00
b03077b60d
[NN] GCNII model added < https://arxiv.org/pdf/2007.02133.pdf > ( #2874 )
...
* Auto stash before rebase of "origin/pytorch-nn-working"
GCNII model added
* linting
* linting
* lint
* Frequency Adaptive gcn init comit
* Revert "Frequency Adaptive gcn init comit"
This reverts commit 86a80586ac0040497c1edfa0e80df719992dcc4a.
* Update python/dgl/nn/pytorch/conv/gcn2conv.py
modified docstring
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
* added beta formula and changed param name
* fix docstring
* lint
* white space lint
* update docstring
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
* docstring formula update
* added gcn2
* added GCN2Conv
* Update nn.pytorch.rst
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-05-17 10:25:59 +08:00
ac1536cf92
[Feature] add udf support for cross_reducer ( #2891 )
...
* add: udf support for `cross_reducer`
* update: code lint
* update: reducer without stack
* docs: add docs for udf cross_reducer
* chore: fix code lint
* docs: update multi_update_all docstring
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
* docs: update reduce_dict_data docstring
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-05-15 14:00:37 +08:00
9983107384
[Feature] Support multidimensional features for GAT ( #2912 )
...
* support multidimensional features for GAT
* docstring
* lint
* fix
2021-05-15 02:47:23 +08:00
caa6d6072c
[Feature] Replacing thread_wrapped_func with minimal mp.Process wrapper ( #2905 )
...
* standardizing thread_wrapped_func
* lints
* Update __init__.py
2021-05-14 11:34:49 +08:00
e156331b0e
return a list of ntypes/etypes ( #2742 )
...
Co-authored-by: Da Zheng <zhengda1936@gmail.com >
2021-05-13 10:42:50 +08:00
103444c58f
Remove __len__ method from DGLGraph ( #2902 )
...
* Update heterograph.py
* remove unit tests
* replace tutorial
2021-05-11 14:06:18 +08:00
70695ff8f8
[Model] Training GraphSAGE with PyTorch Lightning ( #2878 )
...
* pytorch lightning initial examples
* revert most changes in dataloader to favor #2886 .
* address comments
2021-05-11 11:28:13 +08:00
c18f957d0e
[Model] add implementation of twirls ( #2770 )
...
* add implementation of twirls
* format the code
* fix some format error, and ignore others
* fix format errors
* fix format errors
* expose unfolding & attention
* Update nn.pytorch.rst
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-05-11 09:58:48 +08:00
2a3a9a0011
[Bugfix] to() method ignores PyTorch default CUDA device ( #2897 )
2021-05-08 13:23:30 +08:00
bfef789ea1
[Dataloading] Make loader iters iterator ( #2886 )
...
* Make loader items iterator
* Update test_dataloader.py
* Update __init__.py
* Update test_dataloader.py
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-05-07 10:15:49 +08:00
fbfcf1a8cc
Doc: adapt send_and_recv example ( #2822 )
...
* adapt send_and_recv example
* lint fix
* Change title and example order
* Update heterograph.py
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-05-07 09:44:11 +08:00
241b60d489
[Feature][Performance] Accelerate kNN on GPU ( #2868 )
...
* topk kNN accelerated on GPU
* Fix src offset
* Fix trailing whitespace
* Update segmented kNN
* Fix src / dst mixup
* Update kNN docstrings
* Fixed lint
Co-authored-by: Tong He <hetong007@gmail.com >
2021-05-06 14:14:09 +08:00
975eb8fc5d
[Distributed] Distributed node embedding and sparse optimizer ( #2733 )
...
* Draft for sparse emb
* add some notes
* Fix
* Add sparse optim for dist pytorch
* Update test
* Fix
* upd
* upd
* Fix
* Fix
* Fix bug
* add transductive exmpale
* Fix example
* Some fix
* Upd
* Fix lint
* lint
* lint
* lint
* upd
* Fix lint
* lint
* upd
* remove dead import
* update
* lint
* update unitest
* update example
* Add adam optimizer
* Add unitest and update data
* upd
* upd
* upd
* Fix docstring and fix some bug in example code
* Update rgcn readme
Co-authored-by: Ubuntu <ubuntu@ip-172-31-57-25.ec2.internal >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-24-210.ec2.internal >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-2-66.ec2.internal >
2021-05-03 08:37:40 +08:00
ab2bd1f13d
[Feature] Add cuda support for Sparse Matrix multiplication, summation and masking ( #2782 )
...
* init cuda support
* cuSPARSE err
* passed unittest for csr_mm/SpGEMM. int64 not supported
* Debugging cuSPARSE error 3
* csrgeam only supports int32?
* disabling int64 for cuda
* refactor and add CSRMask
* lint
* oops
* remove todo
* rewrite CSRMask with CSRGetData
* lint
* fix test
* address comments
* lint
* fix
* addresses comments and rename BUG_ON
Co-authored-by: Israt Nisa <nisisrat@amazon.com >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-30-71.ec2.internal >
Co-authored-by: Quan Gan <coin2028@hotmail.com >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2021-04-27 16:06:35 +08:00
e18c2ab408
[NN] Fix GATConv for Broadcasting with Residual Connections ( #2867 )
...
* Update
* update
Co-authored-by: Ubuntu <ubuntu@ip-172-31-59-108.us-west-2.compute.internal >
2021-04-27 14:36:06 +08:00
e7046f1e0e
[Distributed] Fix a bug in graph partition. ( #2869 )
...
* update distributed training doc.
* explain data split.
* fix message passing.
* id mapping.
* fix.
* test data reshuffling.
* fix a bug.
* fix test.
* Revert "fix."
This reverts commit 2d025e9e1a5c05c3da9b803a035a788ced59bd77.
* Revert "id mapping."
This reverts commit 2a6a93ceb81fbdff86e6e9e5a58e1ace1e9d9882.
* Revert "fix message passing."
This reverts commit ed8a86bf2b015e5e4f64ba160e81b207ad2a1d65.
* Revert "explain data split."
This reverts commit 4338ddf8a336014cf92d4cb9a1db02b9badc0e55.
* Revert "update distributed training doc."
This reverts commit dda1c35c44536934c19715534f01f832afda6ad2.
* add more tests.
* fix.
* fix.
* fix.
Co-authored-by: Zheng <dzzhen@3c22fba32af5.ant.amazon.com >
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com >
2021-04-26 18:17:16 +08:00
1fe0860750
[Bugfix] Fixes #2844 ( #2847 )
...
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2021-04-25 18:12:17 +08:00
c37e036432
[Bug Fix] Fix sparse opt bug ( #2859 )
...
* Fix #2856
* upd
* Fix unitest
* upd
* upd
* upd
* Fix
Co-authored-by: Ubuntu <ubuntu@ip-172-31-57-25.ec2.internal >
2021-04-25 13:40:21 +08:00
d76af4d4c1
[Distributed] Return the ID mapping in graph partitioning. ( #2857 )
...
* return mapping.
* support heterogeneous graph.
* more test.
* fix lint.
* fix for diff backends.
* fix.
* fix.
Co-authored-by: Zheng <dzzhen@3c22fba32af5.ant.amazon.com >
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com >
2021-04-22 17:51:42 +08:00
bbebde4660
[Performance] Track sorted status of COO from creation ( #2645 )
...
* Add row/col sorted flags
* improve sorting paths
* Remove print statement
* Keep track of sorted matrices
* Remove sort check in to_block
* Improve CPU sorted COO->CSR
* Handle the zero edge case
* Remove omp default clause to work with MSVC
* Update comments on sorted COO->CSR cpu implementatoin
* Expose sorted to python interface
* Make check_sorted default to false for dgl.graph()
* remove check sorted; add utests
* remove check_sorted flag
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2021-04-16 10:30:07 +08:00
e70138bbe4
[Performance][GPU] Enable GPU uniform edge sampling ( #2716 )
...
* Start on uniform GPU sampling
* Save more work
* Get cu file compiling
* Update sampling
* More changes
* Get GPU sampling for uniform probabilities solved
* Fix batch tensor migration
* Fix
* update kernels
* expand blocking
* Undo testing change
* Cut down on sampling overhead
* Fix replacement
* Update unit tests
* Add option to gpu sample in graphsage
* Copy only csc to gpu
* Add ogbn support
* Fix linting
* Remove nvtx from sample
* Improve documentation and error checking
* Expand documentation
* Update assert checking
* delete extra space
* Use standard dataloader when dataset is a dictionary
* ogb -> ogbn
* Fix edge selection determinism
* Fix typos
* Remove nvtx
* Add comment for self.fanout_arrays and assert
* Fix linting
* Migrate to scalarbatcher
* Fix indentation
* Fix batcher
* Fix indexing
* Only use databatcher for GPU
* Convert to DGL NDArray to PyTorch Tensor
* Add optimization for PyTorch's F.tensor() for list of GPU tensors
Co-authored-by: Da Zheng <zhengda1936@gmail.com >
2021-04-14 18:55:09 -07:00
de5e8e2392
[Distributed] Fix a bug for graphs without node/edge data. ( #2838 )
...
* fix.
* test distributed graph without node/edge data.
* remove some tests.
* fix lint
2021-04-12 22:35:01 -07:00
e83d0a8007
[Feature] Add kd-tree implementation (CPU) for kNN ( #2767 )
...
* add submodule nanoflann
* finish python API for knn
* finish ndarray adaptor
* finish cpu-kdtree version of knn
* use openmp
* add endline
* upt
* upt
* fix format and code style
* upt
* add warning for gpu-cpu copy
* avoid contiguous copy
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
Co-authored-by: Tong He <hetong007@gmail.com >
2021-04-09 17:39:34 +08:00
0fce09074d
[Distributed] Bind to the correct NIC ( #2798 )
...
Co-authored-by: Da Zheng <zhengda1936@gmail.com >
2021-04-08 17:56:30 -07:00
bfbbefa793
[Distributed] Fix a bug in multiprocessing sampling. ( #2826 )
...
Co-authored-by: Ubuntu <ubuntu@ip-172-31-73-81.ec2.internal >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-04-08 01:29:33 -07:00
48b9ecd201
Fix discrepancy in dgl.dataloading.EdgeDataLoader ( #2819 )
...
* fix discrepancy
* address comments
2021-04-07 16:08:14 +08:00
3301bd0bcc
bump nightly to 0.7 ( #2814 )
2021-04-06 13:51:26 +08:00
cfe6e70b7a
RGAT baseline for OGB-LSC node classification challenge ( #2810 )
...
* RGAT baseline
* update links (data.dgl.ai hasn't refreshed yet)
* nvm still use dgl.ai domain
* descriptions
* actually it took less
* address comments
* stop worrying about cache
* update links
* oops
2021-04-05 18:21:18 +08:00
b49cd0952f
[Bugfix] Fix feature type of 'ENZYMES' in TUDataset ( #2800 )
...
* PPIDataset
* Revert "PPIDataset"
This reverts commit 264bd0c960cfa698a7bb946dad132bf52c2d0c8a.
* Hide implementations that may cause confusions to the user
* fix number of classes in Amazon Cobuy datasets
* add four papers
* fix feature type of TU dataset
* fix readme
* remove commented codes
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2021-04-01 14:36:55 +08:00
1f4c0b7193
Fix processing of QM9EdgeDataset ( #2801 )
2021-04-01 10:13:51 +08:00
e36c5db614
[Distributed] Simplify distributed API ( #2775 )
...
* remove num_workers.
* remove num_workers.
* remove num_workers.
* remove num-servers.
* update error message.
* update docstring.
* fix docs.
* fix tests.
* fix test.
* fix.
* print messages in test.
* fix.
* fix test.
* fix.
Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-132.us-west-1.compute.internal >
2021-03-29 19:19:23 -07:00
97863ab85b
[Distributed] Cleanup the process pool correctly when the process exits. ( #2781 )
...
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com >
2021-03-29 14:53:51 -07:00
2952f3c473
Update subgraph.py ( #2784 )
...
Co-authored-by: Zihao Ye <expye@outlook.com >
2021-03-29 14:58:39 +08:00
0576a33b7f
Update convert.py ( #2789 )
...
Co-authored-by: Zihao Ye <expye@outlook.com >
2021-03-28 20:59:52 +08:00
e22087aa36
[BUG] fix for zero degree nodes ( #2786 )
...
* fix for zero degree nodes
* Update python/dgl/ops/spmm.py
linting fix
Co-authored-by: Zihao Ye <zihaoye.cs@gmail.com >
Co-authored-by: Konstantin Sofeikov <konstantin.sofeikov@complyadvantage.com >
Co-authored-by: Zihao Ye <expye@outlook.com >
Co-authored-by: Zihao Ye <zihaoye.cs@gmail.com >
2021-03-25 22:09:53 +08:00
03482f0a4c
[NN] tf nn for edgeConv ( #2741 )
...
* tf nn for edgeConv
* Auto stash before merge of "tf_working" and "origin/tf_working"
* clean up
* added test for edge_conv
* fix
* fix
* fix
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
Co-authored-by: Quan Gan <coin2028@hotmail.com >
2021-03-25 13:44:07 +08:00
929d863447
[Feature] Sparse-sparse matrix multiplication, addition, and masking ( #2753 )
...
* test
* more stuff
* add test
* fixes
* optimize algo
* replace unordered_map with arrays
* lint
* lint x2
* oops
* disable gpu csrmm tests
* remove gpu invocation
* optimize with openmp
* remove python functions
* add back with docstrings
* lint
* lint
* update python interface
* functionize
* functionize
* lint
* lint
2021-03-24 17:24:41 +08:00
6999f88f3f
[Model] Add random_start option for Farthest Point Sampler ( #2755 )
...
* add random_start option for FPS
* change doc
* change from random_start to start_idx
* change error condition
* change error msg
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2021-03-22 21:53:46 +08:00
bcffdb82c9
[Example] Add implementation of mvgrl ( #2739 )
...
* [Example ]add mvgrl
* [Doc] add mvgrl to readme
* add more comments
* fix typos
* replace tab with space
* [doc] replace tab with space
* [Doc] fix a typo
* fix minor typos
* fix typos
* fix typos
* fix typos
* fix typos
* fix
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-03-22 21:20:21 +08:00
1789972c4b
[Bugfix] add default value for BlockSampler ( #2771 )
...
* [Bugfix] add default value for BlockSampler
* [Doc] modify user_guide description about MultiLayerDropoutSample
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-03-22 14:02:27 +08:00
edf644633d
[performance] Optimize the association order of AXW in GraphSAGE. ( #2747 )
...
* upd
* lint
* upd
* upd
* compatibility
* upd
* upd
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-03-19 01:41:33 +08:00
366cc7ebf3
[Pickle] Fix HeteroGraphConv pickle problem ( #2761 )
...
* fix pickle problem
* lint
* add pickle tests
* fix
* fix
* fix
* fix
* fix for windows
2021-03-18 17:56:28 +08:00
09ef2c2c3d
[Doc] Add Pseudo Code for HeteroGraphConv ( #2729 )
...
* Update
* Update
* Update
* Update
Co-authored-by: Ubuntu <ubuntu@ip-172-31-15-8.us-west-2.compute.internal >
2021-03-17 20:00:15 +08:00
b34a1e63d4
Update subgraph.py ( #2754 )
2021-03-17 18:15:30 +08:00
3c8382f6b6
Fix typos in zero-in-degree ( #2750 )
2021-03-14 19:13:59 +08:00
0b47e86803
[Example] Add DimeNet(++) for Molecular Graph Property Prediction ( #2706 )
...
* [example] arma
* update
* update
* update
* update
* update
* [example] dimenet
* [docs] update dimenet
* [docs] update tf results
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-03-09 17:08:59 +08:00
c88fca5055
[Feature] Add edge coarsening for homogeneous undirected graphs ( #2691 )
...
* finish graph matching gpu version
* use C++ shuffle
* finish graph matching
* fix bug
* fix bug
* change name and use swap
* upt
* fix format problem
* fix format problem
* stronger test
* upt
* upt
* change python api
* upt
* upt
* format check
* upt
* upt
* fix bug
Co-authored-by: Tong He <hetong007@gmail.com >
2021-03-09 16:35:27 +08:00
a1f59c3b68
[Feature] QM9Edge Dataset Support ( #2704 )
...
* [Feature] Support QM9Edge Datset
* Update qm9_edge.py
* disable tqdm
* Update qm9_edge.py
* Update qm9_edge.py
* Update qm9_edge.py
* Update qm9_edge.py
* Update qm9_edge.py
* Update qm9_edge.py
* Update qm9_edge.py
* remove preprocessing part
* add comparisons in qm9.py
* [docs] add qm9edge dataset
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-03-09 14:51:21 +08:00
7380d61eb9
[NN] Support Unidirectional Bipartite Graphs in CFConv ( #2674 )
...
* Update
* update
* Update
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-03-03 16:35:07 +08:00
Quan (Andy) Gan