d7390763f0
[Distributed] Deprecate old DistEmbedding impl, use synchronized embedding impl ( #3111 )
...
* fix.
* fix.
* fix.
* fix.
* Fix test
* Deprecate old DistEmbedding impl, use synchronized embedding impl
* update doc
Co-authored-by: Ubuntu <ubuntu@ip-172-31-71-112.ec2.internal >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-2-66.ec2.internal >
Co-authored-by: Da Zheng <zhengda1936@gmail.com >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-07-14 00:15:53 +08:00
ee6bc95175
Update a comment in pytorch HGT example ( #3101 )
...
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-07-13 19:09:17 +08:00
b576e617ad
[Feature] Add left normalizer for GCN ( #3114 )
...
* add left normalizer for gcn
* fix
* fixes and some bug stuff
2021-07-13 12:49:35 +08:00
0ce92a86ed
[BugFix] fix problems found in bug bash ( #3116 )
...
* fix breakline in fakenews.py
* fix inconsistent argument name
* modify incorrect example and deprecated graph type
* modify docstring and example in knn_graph
* fix incorrect node type
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-07-12 13:34:50 +08:00
3641829211
fix docs ( #3126 )
...
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-07-12 11:43:15 +08:00
fc55225f08
Fix module name ( #3128 )
2021-07-12 11:15:02 +08:00
5798ee8d98
[Performance] Add a warning for ChebConv ( #3099 )
...
* add a warning for chebconv
* fix and docstrings
* update bgnn
* fix
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-07-09 14:49:15 +08:00
0d1dcdcd2e
[bugfix] fix a bug found in v0.7 bug bash in the 'grace' model ( #3109 )
...
* Update aug.py
* Update aug.py
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-07-07 14:50:02 +08:00
22e8c120be
[Example ] fix faiss issue on k 3 for hilander model ( #3105 )
...
* fix faiss issue on k 3
* Add Hilander paper link
Co-authored-by: Tong He <hetong007@gmail.com >
2021-07-06 13:22:56 +08:00
9c41c22d7b
[Model] Official implementation for HiLANDER model. ( #3087 )
...
* add hilander model implementation draft
* use focal loss
* fix
* change data root
* add necessary scripts
* update download links
* update
* update example table
* fix
* update readme with numbers
* add empty folder
* only eval at the end
* set up hilander
* inform results may fluctuate
* address comments
Co-authored-by: sneakerkg <xiaotj1990327@gmail.com >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-19-212.us-east-2.compute.internal >
2021-07-04 20:08:58 +08:00
0884d02465
[Distributed] Fix bugs in partitioning on heterogeneous graphs. ( #3085 )
...
* fix bugs in partitioning on heterogeneous graphs.
* fix.
* fix.
* fix example.
* fix.
* fix test.
* fix.
* fix.
* fix.
* fix tests.
Co-authored-by: Ubuntu <ubuntu@ip-172-31-71-112.ec2.internal >
Co-authored-by: Zheng <dzzhen@3c22fba32af5.ant.amazon.com >
2021-07-02 21:16:14 +08:00
02e5d47d2a
[Example][Bugfix] Fix RGCN example datasplitting ( #3037 )
...
* Fix example datasplitting
* Remove left-over split parameter
* Remove unused parameter
* Set epoch when using multiple GPUs
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com >
2021-06-29 10:16:28 +08:00
7f4086da7a
cuda() to to(device) ( #3064 )
...
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-06-28 11:56:24 +08:00
2f43cdb3c8
deal with situation where num_layers equals 1 ( #3066 )
2021-06-28 10:17:16 +08:00
427a5a96e0
[Doc] Update NodeDataLoader and EdgeDataLoader for GPU-based neighbor sampling ( #3046 )
...
* update docstrings and tidy code
* add docs
* address comments
* Update __init__.py
* address comments
2021-06-25 10:46:21 +08:00
acd21a6d60
[Feature] Support direct creation from CSR and CSC ( #3045 )
...
* csr and csc creation
* fix
* fix
* fixes to adj transpose
* fine
* raise error if indptr did not match number of nodes
* fix
* huh?
* oh
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2021-06-25 10:05:47 +08:00
31f4483af7
add HAN sampling demo ( #3005 )
...
Co-authored-by: maqy1995 <maqingyun0718>
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-06-23 20:27:18 +08:00
cb2327d4a9
[Example] Fix error in gcn train due to missing argument ( #3040 )
...
* Fix example
* Remove register_data_args and revert to dataset
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2021-06-23 15:50:07 +08:00
e667545da5
[Feature] Node2vec ( #2992 )
...
* add seal example
* 1. add paper infomation in examples/README
2. adjust codes
3. option test
* use latest `to_simple` to replace coalesce graph function
* remove outdated codes
* remove useless comment
* Node2vec
1.implement node2vec random walk c++ op
2.implement node2vec model
3.implement node2vec example
* add CMakeLists file modify
* refine c++ codes
* refine c++ codes
* add missing whitespace
* refine python codes
* add codes
* add node2vec_impl.h
* fix codes
* fix code style problem
* fixes
* remove
* lots of changes
* add benchmark
* fixes
Co-authored-by: smilexuhc <smile.xuhc@gmail.com >
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2021-06-23 14:47:56 +08:00
ff519f98c3
[API] Standardize Subgraph APIs ( #2929 )
...
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Fix
* Update
* Fix subgraph tests
* Capture stdout for distributed test
* Capture stdout for distributed test
* Update
* Update
* Update
* Update subgraph.cc
Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-17.us-west-2.compute.internal >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-06-21 19:53:37 +08:00
aaec3d8a0b
[Distributed] Support hierarchical partitioning ( #3000 )
...
* add.
* fix.
* fix.
* fix.
* fix.
* add tests.
* support node split and edge split.
* support 1 partition.
* add tests.
* fix.
* fix test.
* use hierarchical partition.
* add check.
Co-authored-by: Zheng <dzzhen@3c22fba32af5.ant.amazon.com >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-22-57.us-west-2.compute.internal >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-71-112.ec2.internal >
2021-06-16 16:58:23 +08:00
18eaad17cc
fix bugs ( #3008 )
...
Co-authored-by: zhjwy9343 <6593865@qq.com >
2021-06-16 15:27:47 +08:00
36c6c64957
Replace QM9_v2 with built-in QM9Edge Dataset ( #3026 )
...
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-06-16 14:35:40 +08:00
305d5c16df
[Example] update ogbn-arxiv and ogbn-proteins results ( #3018 )
...
* [Example] GCN on ogbn-arxiv dataset
* Add README.md
* Update GCN implementation on ogbn-arxiv
* Update GCN on ogbn-arxiv
* Fix typo
* Use evaluator to get results
* Fix duplicated
* Fix duplicated
* Update GCN on ogbn-arxiv
* Add GAT for ogbn-arxiv
* Update README.md
* Update GAT on ogbn-arxiv
* Update README.md
* Update README
* Update README.md
* Update README.md
* Add GAT implementation for ogbn-proteins
* Add GAT implementation for ogbn-proteins
* Add GAT implementation for ogbn-proteins
* Add GAT implementation for ogbn-proteins
* Add GAT implementation for ogbn-proteins
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Update examples for ogbn-arxiv
* Add examples for ogbn-products.
* Update examples for ogbn-proteins.
* Update examples for ogbn-proteins.
* Update examples for ogbn-proteins.
* Update examples for ogbn-proteins.
* Update examples for ogbn-proteins.
* Update examples for ogbn-proteins.
* Update examples for ogbn-proteins.
* Update examples for ogbn-proteins.
* Update examples for ogbn-proteins.
* Update examples for ogbn-products.
* Update examples for ogbn-products.
* Update examples for ogbn-arxiv.
* Update examples for ogbn-arxiv.
* Update examples for ogbn-arxiv.
* Update examples for ogbn-proteins.
* Update examples for ogbn-products.
* Update examples for ogbn-proteins.
* Update examples for ogbn-arxiv.
* Update examples for ogbn-proteins.
* Update README.md
* [Example] ogbn-arxiv & ogbn-proteins
* [Example] ogbn-arxiv & ogbn-proteins
* [Example] ogbn-arxiv & ogbn-proteins
* [Example] ogbn-arxiv & ogbn-proteins
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
Co-authored-by: Zihao Ye <expye@outlook.com >
2021-06-16 12:33:43 +08:00
b4ad59d77f
[Model] reformat and update performance of grace ( #3009 )
...
* reformat and update performance
* Update README.md
* Fix typos
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-06-15 17:02:37 +08:00
8b64ae59b8
[Performance] Perform to_block on the GPU when the dataloader is created with a GPU device. ( #3016 )
...
* add output device for dataloading
* Update dataloader
* Get sampler device from dataloader
* Fix line length
* Update examples
* Fix to_block GPU for empty relation types
* Handle the case where the DistGraph has None for the underlying graph
Co-authored-by: Da Zheng <zhengda1936@gmail.com >
2021-06-13 18:51:00 +08:00
79b057f0cf
Fix example to test_acc is always computed at last epoch ( #3014 )
2021-06-12 18:02:00 -07:00
17d604b5c7
[Feature] Allow using NCCL for communication in dgl.NodeEmbedding and dgl.SparseOptimizer ( #2824 )
...
* Split from NCCL PR
* Fix type in comment
* Expand documentation for sparse_all_to_all_push
* Restore previous behavior in example
* Re-work optimizer to use NCCL based on gradient location
* Allow for running with embedding on CPU but using NCCL for gradient exchange
* Optimize single partition case
* Fix pylint errors
* Add missing include
* fix gradient indexing
* Fix line continuation
* Migrate 'first_step'
* Skip tests without enough GPUs to run NCCL
* Improve empty tensor handling for pytorch 1.5
* Fix indentation
* Allow multiple NCCL communicator to coexist
* Improve handling of empty message
* Update python/dgl/nn/pytorch/sparse_emb.py
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com >
* Update python/dgl/nn/pytorch/sparse_emb.py
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com >
* Keepy empty tensor dimensionaless
* th.empty -> th.tensor
* Preserve shape for empty non-zero dimension tensors
* Use shared state, when embedding is shared
* Add support for gathering an embedding
* Fix typo
* Fix more typos
* Fix backend call
* Use NodeDataLoader to take advantage of ddp
* Update training script to share memory
* Only squeeze last dimension
* Better handle empty message
* Keep embedding on the target device GPU if dgl_sparse if false in RGCN example
* Fix typo in comment
* Add asserts
* Improve documentation in example
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com >
2021-06-10 21:19:00 -07:00
9497a9be85
[Bugfix][Examples] Fix graphsage multigpu training example training set size ( #3002 )
...
* Make multigpu graphsage use whole datset
* Specify queeze dimension
* Remove squeeze dimension
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-06-10 16:35:08 -07:00
6c59fee99b
[Model] HetGNN/GTN/HAN/NSHE/MAGNN examples ( #2993 )
...
* commit hetgnn
* Update README.md
* Delete examples/pytorch/hetgnn directory
* Update README.md
* Update README.md
* Update README.md
* Revert "Update README.md"
This reverts commit 14cdb3da76c58665ff879eae17ecf9eb28b66cce.
* Update README.md
* Add files via upload
* Update README.md
* Update README.md
2021-06-08 08:54:27 +08:00
972a9f1323
[Doc] Re-organize the code for dgl.geometry, and expose it in the doc ( #2982 )
...
* reorg and expose dgl.geometry
* fix lint
* fix test
* fix
2021-06-07 11:19:39 +08:00
6e9d16459e
[Fix] Fixed AttributeError with new version of torchtext (0.9+). ( #2985 )
2021-06-05 02:01:20 +08:00
60426278bf
[Example] TAHIN ( #2864 )
...
* tahin
* readme
* readme
* readme
* readme
* readme
* readme
* main
* main
* new_line
* update
Co-authored-by: zhjwy9343 <6593865@qq.com >
2021-06-03 16:03:55 +08:00
22d0df8b6a
[Doc] Update link_predict.py docstring ( #2960 )
...
corrected docstring, the model uses two R-GCN layers
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2021-06-02 12:08:28 +08:00
18dbaebebc
[Distributed] Specify the graph format for distributed training ( #2948 )
...
* explicitly set the graph format.
* fix.
* fix.
* fix launch script.
* fix readme.
Co-authored-by: Zheng <dzzhen@3c22fba32af5.ant.amazon.com >
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-71-112.ec2.internal >
2021-05-26 18:09:30 +08:00
c018436588
[Example] add latent dirichlet allocation ( #2883 )
...
* add lda model
* tweak latent dirichlet allocation
* Update README.md
* Update README.md
* update example index
* update header
* minor tweak
* add example test
* update doc
* Update README.md
* Update README.md
* add partial_fit for free
* Update examples/pytorch/lda/lda_model.py
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
* Update examples/pytorch/lda/example_20newsgroups.py
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
* Update lda_model.py
* bugfix torch Gamma uses rate parameter
Co-authored-by: Yifei Ma <yifeim@amazon.com >
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-05-17 20:25:36 +08:00
7c7113f660
add use_ddp to dataloaders ( #2911 )
2021-05-17 15:46:02 +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
85231dc93b
[Example] Label Propagation and Correct&Smooth ( #2852 )
...
* [example] label propagation and correct&smooth
* update
* update
* update
* update
* [docs] add speed for c&s
* update
* [fix] remove gat&consistent with the author's code
* [feat] multi-type adj norm supported
* update
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-05-12 18:45:46 +08:00
d70ca6eb7c
[Example] graphsaint ( #2792 )
...
* graphsaint
* graphsaint
* graphsaint
* graphsaint
* fixed the model
* fixed some bugs
* fixed the computing of normalization and updated the results
* fixed some bugs and updated the results
* Update utils.py
* Update train_sampling.py
* Update train_sampling.py
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-05-11 16:25:56 +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
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
b2b531e041
[Example] add implementation of grace ( #2828 )
...
* [Example] add implementation of grace
* [Doc] add grace in the index file
* fix
* fix typos
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-04-27 12:43:03 +08:00
2ae891a78c
Update main.py ( #2872 )
2021-04-26 17:12:19 +08:00
756fdd8e90
[Example] DeeperGCN ( #2831 )
...
* [example] deepergcn
* update
* update
* update
* update
* update
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-04-25 18:37:41 +08:00
3c387988d7
[Example] DCRNN and GaAN ( #2858 )
...
* Ready for PR
* refractor code
Co-authored-by: Ubuntu <ubuntu@ip-172-31-45-47.ap-northeast-1.compute.internal >
Co-authored-by: Tianjun Xiao <xiaotj1990327@gmail.com >
2021-04-23 22:33:39 +08:00
ebc6a85a80
[Bugfix] TGN model bugfix and improvement ( #2860 )
...
* Add DCRNN Example
* Bugfix DCRNN
* Bugfix DCRNN
* Bugfix Train/eval have different flow
* Performance Matched
* modified tgn for research
* kind of fixed 2hop issue
* remove data
* bugfix and improve the performance
* Refractor Code
Co-authored-by: Ubuntu <ubuntu@ip-172-31-45-47.ap-northeast-1.compute.internal >
Co-authored-by: Tianjun Xiao <xiaotj1990327@gmail.com >
2021-04-23 15:44:22 +08:00
4579bbf7b7
Update README.md ( #2853 )
...
Change the format of README.md
2021-04-21 13:05:25 +08:00
6232ee8d44
Update README.md ( #2820 )
...
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-04-20 13:17:30 +08:00
e58eeebfb6
[Model] Add RECT example ( #2813 )
...
* Update README.md
Add description of RECT
* [Example] Add implementation of RECT
[Example] Add implementation of RECT
* Update classify.py
Modify the class names and the function names mentioned above
* Update main.py
Modify the function names mentioned above
* Update label_utils.py
Adjust the comments
* Update README.md
Add the github information
Co-authored-by: Tianjun Xiao <xiaotj1990327@gmail.com >
2021-04-19 21:48:38 +08:00
xiang song(charlie.song)