684f66b7aa
[Feature] Added exclude_self and output_batch to knn graph construction (Issues #4323 #4316 ) ( #4389 )
...
* * Added "exclude_self" and "output_batch" options to knn_graph and segmented_knn_graph
* Updated out-of-date comments on remove_edges and remove_self_loop, since they now preserve batch information
* * Changed defaults on new knn_graph and segmented_knn_graph function parameters, for compatibility; pytorch/test_geometry.py was failing
* * Added test to ensure dgl.remove_self_loop function correctly updates batch information
* * Added new knn_graph and segmented_knn_graph parameters to dgl.nn.KNNGraph and dgl.nn.SegmentedKNNGraph
* * Formatting
* * Oops, I missed the one in segmented_knn_graph when I fixed the similar thing in knn_graph
* * Fixed edge case handling when invalid k specified, since it still needs to be handled consistently for tests to pass
* Fixed context of batch info, since it must match the context of the input position data for remove_self_loop to succeed
* * Fixed batch info resulting from knn_graph when output_batch is true, for case of 3D input tensor, representing multiple segments
* * Added testing of new exclude_self and output_batch parameters on knn_graph and segmented_knn_graph, and their wrappers, KNNGraph and SegmentedKNNGraph, into the test_knn_cuda test
* * Added doc comments for new parameters
* * Added correct handling for uncommon case of k or more coincident points when excluding self edges in knn_graph and segmented_knn_graph
* Added test cases for more than k coincident points
* * Updated doc comments for output_batch parameters for clarity
* * Linter formatting fixes
* * Extracted out common function for test_knn_cpu and test_knn_cuda, to add the new test cases to test_knn_cpu
* * Rewording in doc comments
* * Removed output_batch parameter from knn_graph and segmented_knn_graph, in favour of always setting the batch information, except in knn_graph if x is a 2D tensor
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2022-09-07 08:35:26 +08:00
a88e7f7e28
[Example]rgcn-ogbn-mag ( #4331 )
...
* rgcn-ogbn-mag
* Add link in README.md
* correct code-format,add the reset_parameters function to the HeteroEmbedding module
* add the annotation in hetero.py
* add a unit test
* modify format
* Update
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-50-143.us-west-2.compute.internal >
2022-08-10 20:12:31 +08:00
5ba5106aca
[Bugfix] Fix the default value of num_bases in RelGraphConv module ( #4321 )
...
* Fix doc and default settings for RelGraphConv
* Add unit test
* Split msg in two lines to pass CI-lint
2022-08-07 16:33:16 +08:00
d6957c28ff
[BugFix] fix incorrect _bias and bias usage ( #4310 )
2022-07-30 17:40:54 +08:00
fdbf5a0fda
[DGL-Go][Doc] Update DGL-Go version to 0.0.2 and misc fix from bug bash ( #4236 )
...
* Update
* Update
* Update
* Update
Co-authored-by: Ubuntu <ubuntu@ip-172-31-53-142.us-west-2.compute.internal >
Co-authored-by: Xin Yao <xiny@nvidia.com >
2022-07-14 21:30:38 +08:00
a25a14f2fa
[Bug Fix] Fix A Bug Related to GroupRevRes ( #4181 )
...
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
Co-authored-by: Xin Yao <xiny@nvidia.com >
2022-06-28 21:17:20 +08:00
efd909e62e
[NN] Enhance EGATConv branch ( #4062 )
...
* enhance EGATConv| nfeats as tuples
* egatconv modified for bipartite graphs
* modified docstrings
* added/modified unittests for EGATConv
* Update egatconv.py
* rectified lint errors
Co-authored-by: rijulizer <riju.mukherjee@gmail.com >
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2022-06-03 11:53:10 +08:00
230b886ec5
[Bug fix] Misc Fix for Transforms and NN Modules ( #4038 )
...
* Update module.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update module.py
* Update
* Update
* Update
2022-05-24 18:08:08 +08:00
3fe5eea791
[NN] Label Propagation & Directional Graph Networks ( #4017 )
...
* add label propagation module
* fix prev bug in example
* add dgn
* fix linting and doc issues
* update label propagation & dgn
* update label propagation & dgn
* update example
* fix unit test
* fix agg heritage issue
* fix agg issue
* fix lint
* fix idx
* fix lp gpu issue
* Update
* Update
Co-authored-by: mufeili <mufeili1996@gmail.com >
2022-05-20 15:23:19 +08:00
5b97a1a26e
add bias argument ( #3970 )
2022-05-05 10:17:24 +08:00
248bece633
[NN] GINEConv ( #3934 )
...
* Update
* Update
* Update
* Update
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2022-04-25 14:41:05 +08:00
43b9d40e5e
[Doc] Fix Doc for EGNNConv ( #3919 )
...
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2022-04-11 11:01:15 +08:00
dc5035b1f3
[NN] Add EGNN & PNA ( #3901 )
...
* add EGNN & PNA
* fix egnn issues
* fix pna issues
* update pna conv
* add doc strings
* update pnaconv
* fix unused args issue
* fix moment aggregation issue
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2022-04-07 17:44:57 +08:00
4c7bd314b4
[Feature] Radius Graph ( #3829 )
...
* radius graph
* remove trailing whitespaces from docs
* disable invalid name for transform func
* disable radius graph module invalid name
* move pylint disable before init
* fix missing nodes from point set
* update docs indexing
* add compute mode as optional param
* radius graph test
* remove trailing whitespaces
* fix precision when comparing tensors
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2022-03-30 17:23:29 +08:00
12e97c54ac
[Feature] get_attention parameter in GlobalAttentionPooling ( #3837 )
...
* get_attention parameter in GlobalAttentionPooling
* removed trailing whitespace
* lint fix
Co-authored-by: decoherencer <decoherencer@users.noreply.github.com >
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2022-03-24 12:49:40 +08:00
61edb7980a
[NN] Update GNNExplainer ( #3848 )
...
* Update
* Update
* Update
2022-03-23 18:40:49 +08:00
8005978e1e
[NN] Grouped reversible residual connections for GNNs ( #3842 )
...
* Update
* Fix
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
2022-03-23 16:58:39 +08:00
6d9433b04f
[Transform] [Doc] Rename transform to transforms and update doc ( #3765 )
...
* Update
* Update
* Update
* Fix
* Update
* Update
* Update
* Fix
2022-02-24 21:28:15 +08:00
0227ddfb66
[NN] Rework RelGraphConv and HGTConv ( #3742 )
...
* WIP: TypedLinear and new RelGraphConv
* wip
* further simplify RGCN
* a bunch of tweak for performance; add basic cpu support
* update on segmm
* wip: segment.cu
* new backward kernel works
* fix a bunch of bugs in kernel; leave idx_a for future
* add nn test for typed_linear
* rgcn nn test
* bugfix in corner case; update RGCN README
* doc
* fix cpp lint
* fix lint
* fix ut
* wip: hgtconv; presorted flag for rgcn
* hgt code and ut; WIP: some fix on reorder graph
* better typed linear init
* fix ut
* fix lint; add docstring
2022-02-23 12:10:20 +08:00
80fb4dbe26
[Doc] fix examples ( #3747 )
2022-02-17 18:46:13 +08:00
9e358dfe66
[NN] HeteroLinear and HeteroEmbedding ( #3678 )
...
* modify hetero
* modify rst document
* update hetero
* update hetero
* update hetero
* update hetero
* Update
* Update
* Update
* Update
* 20220216
* Update
* Update
* Fix
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
Co-authored-by: ShelkerX <925089962@qq.com >
2022-02-17 16:16:51 +08:00
22272de652
[Fix] normalize by dst if edge_weight is None ( #3744 )
...
* [Fix] normalize by dst if edge_weight is None
* [Doc] fix math formula display issue
2022-02-17 13:51:37 +08:00
42f8c8f335
[doc] fix module typo ( #3734 )
...
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2022-02-16 11:10:06 +08:00
97a6d740ad
[doc] fix error in example results ( #3735 )
...
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2022-02-16 09:40:45 +08:00
4f7ad2582c
[doc] fix error in example ( #3736 )
2022-02-15 18:44:15 +08:00
fa343873a8
Fix docs on GraphSAGE normalization ( #3711 )
...
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2022-02-07 17:56:04 +08:00
25c9221b83
Add check for aggregator_type enum in SAGEConv init ( #3691 )
...
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2022-02-03 12:02:35 +08:00
05c6c3c5ec
[NN] Fix GINConv ( #3692 )
...
* Update
* Update
* Fix
* Update
* Update
* Update
* Update
* Fix
* Update
* Update
* Update
* Update
* Fix lint
* lint
* Update
* Update
* lint fix
* Fix CI
* Fix
* Fix CI
* Update
* Fix
* Update
* Update
* Update ginconv.py
* Update test_nn.py
Co-authored-by: Ubuntu <ubuntu@ip-172-31-31-136.us-west-2.compute.internal >
2022-01-27 12:46:29 +08:00
8f5baa15e4
[Doc] Fix spelling, references and update info on building docs ( #3682 )
...
* Fix ref to message-passing guide
* Fix pygments and spacing
* Update build documentation steps in README.md
* Use links
* Adjust parameters in SAGEConv docstring in same order as init
* Fix spelling error
* Change doc link
2022-01-25 17:22:18 +08:00
9c1065479e
[NN] Added activation function as an optional parameter to GINConv ( #3565 )
...
* Added activation function as an optional parameter
* lint fixes
* Modified the input parameters in tandem with other classes
* lint corrections
* corrected tests
* Reverting back to the old interface
* lint corrections
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-12-29 14:01:01 +08:00
5f4c879399
Fix output dimensions of residual connection for GATv2Conv ( #3584 )
...
Number of heads needs to be considered for the transformation of the destination features. Otherwise this will crash if residual==True.
2021-12-13 12:41:30 +08:00
d6eecf90a1
[NN] TransE and TransR ( #3530 )
...
* Update
* Update
* Update
* Update
* Update
* CI
* CI
* CI
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-12-07 10:13:13 +08:00
c3103b62bf
[BugFix] Fix a bug in TWIRLS, add unittest ( #3573 )
...
* Fix a bug in TWIRLS, add unittest
* reformatting the code
* modify unittest for TWIRLS
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-12-07 00:23:09 +08:00
d2ef24335c
[NN] EdgePredictor ( #3518 )
...
* Update
* Update
* Fix
* Update
* Update
* update
* Fix test
* CI
* CI
2021-12-02 14:25:31 +08:00
8dbf3a4716
[NN] Fix GATv2Conv residual for mini-batch ( #3535 )
2021-11-22 23:44:34 +08:00
ea8b5d7933
fix #2278
2021-11-22 10:53:27 +00:00
7b4b8129e3
Add edge_weight parameters to nn modules ( #3455 )
...
* add
* fix optional docing
* fix
* lint
* add normalized by edge weight
* add test
* fix
* lint
* fix docs
* fix
* fix docs
2021-11-21 14:59:46 +08:00
9e7fbf9567
[NN] JumpingKnowledge ( #3512 )
...
* Update
* Fix
2021-11-19 16:37:25 +08:00
dfa32ae092
[NN] GNNExplainer ( #3490 )
...
* Update
* Update
* Update
* Fix
* Update
* Update
* Update
* Update
* Update
* Update
* Fix
* Fix
* Update
* Update
* Update
* Update
* Update
* Update
* lint fix
* lint fix
* Fix lint
* Update
* Fix CI
* Fix CI
* Fix
* CI
* Fix
* Update
* Fix
* Fix
* Fix CI
* Fix CI
2021-11-11 02:22:22 +08:00
55f2e87292
[Doc] Fix Doc for GATv2Conv ( #3491 )
...
* Fix
* CI
Co-authored-by: Ubuntu <ubuntu@ip-172-31-31-136.us-west-2.compute.internal >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2021-11-10 17:28:18 +08:00
db78fac5df
Update gatv2conv.py doc ( #3486 )
2021-11-09 11:08:04 +08:00
e2f33fd5cc
[NN][Model] GATv2 ( #3473 )
...
* [Model][Core] GATv2
* lint
* gatv2conv.py
* lint
* lint
* style and docs
* lint
* gatv2conv fix
Co-authored-by: Shaked Brody shakedbr@campus.technion.ac.il <shakedbr@tangerine.cslcs.technion.ac.il >
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-11-03 21:55:56 +08:00
51c6509704
[NN] Add EGATConv nn.module ( #3425 )
...
* added nn pytorch egatconv
* aligned with test build
* aligned with test build
* fixed wihite spaces
* fixed wihite spaces
* fixed wihite spaces
* added missing egatconv in imports
* added indentation in forward
* GATConv based implementation
* removed **kw_args
* added dgl relative imports
* PR corrections
* added DGL Error to EGATConv imports
* Update test_nn.py
Co-authored-by: Argusmocny <k.kaminski@cent.uw.edu.pl >
Co-authored-by: Mufei Li <mufeili1996@gmail.com >
2021-10-28 00:38:08 +08:00
8798872f54
[Bug] Do not skip graphconv even no edge exists ( #3416 )
2021-10-14 14:34:42 +08:00
9cc85aed62
[Doc] fix formula in RelGraphConv ( #3285 )
...
* [Doc] fix formula in RelGraphConv
* refine descriptions
2021-08-25 17:59:17 +08:00
b4cd60a952
fix relgraphconv bug ( #3256 )
2021-08-23 17:29:14 +08:00
8341244a2d
[Doc] fix formula display issue in EdgeWeightNorm ( #3275 )
...
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-08-21 21:59:26 +08:00
75fca8e4e8
[bugfix] fix the bug of DotGatConv when compute the edge_softmax ( #3272 )
...
Co-authored-by: Zihao Ye <expye@outlook.com >
2021-08-20 09:19:00 +08:00
31772b142e
fixed typos in docs and docstring ( #3231 )
...
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
2021-08-16 13:58:45 +08:00
3f6f694159
[Bug fix] Various fix from bug bash ( #3133 )
...
* Update
* Update
* Update dependencies
* Update
* Update
* Fix ogbn-products gat
* Update
* Update
* Reformat
* Fix typo in node2vec_random_walk
* Specify file encoding
* Working for 6.7
* Update
* Fix subgraph
* Fix doc for sample_neighbors_biased
* Fix hyperlink
* Add example for udf cross reducer
* Fix
* Add example for slice_batch
* Replace dgl.bipartite
* Fix GATConv
* Fix math rendering
* Fix doc
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 >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-22-156.us-west-2.compute.internal >
2021-07-15 09:17:15 +08:00
ndickson-nvidia