mirrors / dmlc--dgl

文件历史

4,154 提交 34 分支 42 Git 标签
2.3.x
提交图

127 次代码提交

作者 SHA1 备注 提交日期
Rhett Ying 9ef80a6e54 [BugFix] remove non-existent arg (#6188) 2023-08-22 11:43:49 +08:00
paoxiaode d5ae1ea05f [BugFix] add input/output shape check in GatedGraphConv (#6119) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-08-09 19:16:46 +08:00
Hongzhi (Steve), Chen 416e2425b1 [Misc] Further polish gcn2conv.py (#6046) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>
 2023-07-27 13:13:50 +08:00
Quan (Andy) Gan 6af55f18cd Update gcn2conv.py (#6020) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
 2023-07-26 12:11:33 +08:00
paoxiaode c4c9b830ae [NN] GatedGCNConv (#5654) 2023-05-06 18:20:06 +08:00
鄢振宇Michael Yan d6c12f0714 [NN] Fix #5642 (#5652) 2023-05-06 13:03:20 +08:00
Tingyu Wang ea706cae58 [Model] Update cugraph-ops models for 23.04 release (#5540) 
Co-authored-by: schmidt-ju <79865721+schmidt-ju@users.noreply.github.com>
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-36-188.ap-northeast-1.compute.internal>
Co-authored-by: peizhou001 <110809584+peizhou001@users.noreply.github.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-16-19.ap-northeast-1.compute.internal>
 2023-05-04 17:11:22 +08:00
czkkkkkk f41934df87 [Sparse] Add conversion between DGLGraph and SparseMatrix. (#5553) 2023-04-20 18:00:34 +08:00
Venzino.Han f1b0a07984 [NN] add egatconv edge_weight (#5539) 
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-04-13 20:54:42 +08:00
schmidt-ju 97286f98d3 [NN] Add EdgeGAT operator (#5282) 
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
 2023-04-09 22:54:49 +08:00
DominikaJedynak 29e6661523 [Optimization] Optimize bias term in GatConv layer (#5466) 2023-04-05 23:17:10 +08:00
Venzino.Han d45eafd47f [NN] add gatconv edge_weight (#5503) 
Co-authored-by: venzino-han <venzino.han@buzzvil.com>
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-03-31 19:53:49 +08:00
Hongzhi (Steve), Chen 89b321b847 [Misc] Rename number_of_edges and number_of_nodes to num_edges and num_nodes. (#5488) 
* nn-only

* data-only

---------

Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>
 2023-03-28 12:58:54 +08:00
Tingyu Wang bfd411d0d5 [Model] Add dgl.nn.CuGraphGATConv model (#5168) 
* add CuGraphGATConv model

* lintrunner

* update model to reflect changes in make_mfg_csr(), move max_in_degree to forward()

* simplify pytest markers

* fall back to FG option for large fanout

* update error msg

* add feat_drop and activation options

* add residual option

* Update python/dgl/nn/pytorch/conv/cugraph_gatconv.py

Co-authored-by: Mufei Li <mufeili1996@gmail.com>

* Update python/dgl/nn/pytorch/conv/cugraph_gatconv.py

Co-authored-by: Mufei Li <mufeili1996@gmail.com>

* reset res_fc

---------

Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-03-04 14:10:06 +08:00
Tingyu Wang bcf9923b32 [Model] Add dgl.nn.CuGraphSAGEConv model (#5137) 
* add CuGraphSAGEConv model

* fix lint issues

* update model to reflect changes in make_mfg_csr(), move max_in_degree to forward()

* lintrunner

* allow reset_parameters()

* remove norm option, simplify test

* allow full graph fallback option, add example

* address comments

* address reviews

---------

Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-02-22 13:43:28 +08:00
Hongzhi (Steve), Chen 63ac788ff4 auto-reformat-nn (#5319) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>
 2023-02-19 08:33:30 +08:00
Tingyu Wang 19b3cea166 [Model] Update CuGraphRelGraphConv to use pylibcugraphops=23.02 (#5217) 
* update cugraph_relgraphconv

* update equality test

* update cugraph rgcn example

* update RelGraphConvAgg based on latest API changes

* enable fallback option to fg when fanout is large

---------

Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-02-15 20:11:20 +08:00
Zahi Kakish 21733e903b Documentation equation syntax fix for EGATConv (#5284) 
Some weird formatting occurred in the documentation for EGATConv, so this quick commit should fix that.

Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-02-13 14:58:11 +08:00
Rhett Ying b7042a141c [BugFix] fix unexpected exception when agg_type is GCN and bias disabled (#5127) 
* [BugFix] fix unexpected exception when agg_type is GCN and bias is disabled

* Update sageconv.py

Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
 2023-01-10 09:05:44 +08:00
bgawrych e296c468b2 [Optimization] Optimize bias term in SageConv layer (#4747) 
* Optimize bias term in sageconv

* fix lint

* Remove bias sharing

* Update sageconv.py

Co-authored-by: Bartlomiej Gawrych <barlomiej.gawrych@intel.com>
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
 2023-01-08 13:06:46 +08:00
peizhou001 ab0c0ec68f [API Deprecation] Deprecate candidates in convert module (#4988) (#5115) 2023-01-06 14:45:52 +08:00
Xin Yao dde5cf5d02 [Bug] Fix NN modules crashing with non-FP32 inputs (reopen #4262) (#4829) 
* fix fp16 in nn modules

* fix lint

* remove the example

Co-authored-by: Quan Gan <coin2028@hotmail.com>
 2023-01-06 14:18:19 +08:00
peizhou001 996c533149 [Model] Fix bug of gatv2 when input is block (#5000) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-16-19.ap-northeast-1.compute.internal>
 2022-12-12 15:32:48 +08:00
Tingyu Wang ba21295cd5 [Model] Update CuGraphRelGraphConv to use new bindings from pylibcugraphops (#4965) 
* 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>
 2022-12-06 14:00:57 +08:00
peizhou001 611393021a [API Deprecation] Remove candidates in DGLGraph (#4946) 2022-12-01 16:41:53 +08:00
Tingyu Wang 4ecd2c8585 [Model] Add dgl.nn.CuGraphRelGraphConv model (#4826) 
* added relgraphconv

* add tests for CuGraphRelGraphConv

* move test to tests directory

* update docs

* address PR review 1

* address PR review, continued

* remove stashing ctx.device

* make fanout optional

* fanout -> max_in_degree

* improve docstrings consistency

* initialize parameters directly in __init__

* get rid of shared memory size check

* improve docs

* format comments

* skip test case for regularizer=None

Co-authored-by: Mufei Li <mufeili1996@gmail.com>
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2022-11-18 14:04:51 +08:00
dddg617 ee9887d66a [Fix]Support HGT mini-batch (#4664) 
* [Fix]Support HGT mini-batch

* [Test] Update HGT test

* [Conv] nightly update conv

* [Conv] nightly update
 2022-11-14 16:18:39 +08:00
Hongzhi (Steve), Chen 76bb54044e [Misc] Black auto fix. (#4682) 
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
 2022-10-08 14:16:12 +08:00
Chang Liu 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
Rhett Ying d6957c28ff [BugFix] fix incorrect _bias and bias usage (#4310) 2022-07-30 17:40:54 +08:00
Mufei Li 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
Mufei Li 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
Riju Mukherjee 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
rudongyu 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
Mufei Li 248bece633 [NN] GINEConv (#3934) 
* Update

* Update

* Update

* Update

Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
 2022-04-25 14:41:05 +08:00
Mufei Li 43b9d40e5e [Doc] Fix Doc for EGNNConv (#3919) 
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
 2022-04-11 11:01:15 +08:00
rudongyu 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
Mufei Li 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
Mufei Li 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
Minjie Wang 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
Rhett Ying 80fb4dbe26 [Doc] fix examples (#3747) 2022-02-17 18:46:13 +08:00
Rhett Ying 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
Rhett Ying 4f7ad2582c [doc] fix error in example (#3736) 2022-02-15 18:44:15 +08:00
KoyamaSohei 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
Jeremy Goh 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
Mufei Li 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
Jeremy Goh 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
RONANKI SWAMY SRIHARSHA 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
schmidt-ju 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
Yongyi 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