mirrors / dmlc--dgl

文件历史

3,142 提交 34 分支 42 Git 标签
1.1.x
提交图

67 次代码提交

作者 SHA1 备注 提交日期
caojy1998 4693fa43be [Bug fix] Fix the bug in creating unibipartite heterogenous graph (#6093) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-21-37.ap-northeast-1.compute.internal>
 2023-08-10 01:58:49 +00:00
Andrei Ivanov 3e04a6715a Removing warnings appearing in heterograph tests (#6095) 
Co-authored-by: Xin Yao <xiny@nvidia.com>
 2023-08-10 01:58:49 +00:00
Jing Zhu 9e33ccde45 [SpotTarget]Edge sampler with excluding edges adjacent to low-degree nodes (#5893) 
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
Co-authored-by: ZYH <31127200+Tonyzhou98@users.noreply.github.com>
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-08-10 01:58:49 +00:00
Zhiteng Li c7c6cdf407 [NN] Add EGT Layer (#6056) 
Co-authored-by: rudongyu <ru_dongyu@outlook.com>
 2023-08-10 01:58:48 +00:00
Ilia Taraban ea3d6ac232 [Feature] Enable bfloat16 convert functions in Python API (#5760) 2023-08-10 01:58:48 +00:00
Quan (Andy) Gan 180660217b [Bugfix] Fix 5873 (#5884) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-08-10 01:58:48 +00:00
nv-dlasalle 3936bb7a7e [Bugfix] Allow pinning of empty tensor (#6044) 2023-08-10 01:58:48 +00:00
Muhammed Fatih BALIN 75b34c1d4e [Feature] Gpu cache for node and edge data (#4341) 
Co-authored-by: xiny <xiny@nvidia.com>
 2023-08-10 01:58:48 +00:00
AdamGrabowski 748098fce7 [Performance] Fused sampling with compaction (#5924) 
Co-authored-by: Hesham Mostafa <hesham.mostafa@intel.com>
 2023-08-10 01:58:48 +00:00
Muhammed Fatih BALIN 39b0a52831 [Performance][CUDA] Labor UVA optimization (#5885) 
Co-authored-by: Xin Yao <xiny@nvidia.com>
Co-authored-by: Rhett Ying <85214957+Rhett-Ying@users.noreply.github.com>
 2023-08-10 01:58:48 +00:00
caojy1998 15948130e4 [BugFix]Use Python API for relabel_nodes (#5937) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-6-31.ap-northeast-1.compute.internal>
 2023-08-10 01:58:47 +00:00
Andrzej Kotłowski 62a2430e74 [Test] Run test_spmm also on floats (#5930) 2023-08-10 01:58:47 +00:00
rudongyu 5a310c4689 [NN] Refactor SpatialEncoder3d (#5894) 2023-08-10 01:58:47 +00:00
Andrzej Kotłowski b413bf27c3 [TESTS] Make pytorch test_nn.py fully reproducible (#5887) 2023-08-10 01:58:47 +00:00
keli-wen 9497bde655 [Sparse] Update code and add unittest for formats (#5859) 2023-06-20 07:47:55 +00:00
caojy1998 a7567f6c84 [Test] Add testcase for function AddSelfLoop (#5858) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-6-31.ap-northeast-1.compute.internal>
 2023-06-20 07:47:55 +00:00
Zhiteng Li 051258f537 [NN] Refactor DegreeEncoder, SpatialEncoder and PathEncoder (#5799) 
Co-authored-by: rudongyu <ru_dongyu@outlook.com>
 2023-06-20 07:47:55 +00:00
rudongyu a138415798 [BugFix] Fix khop_adj (#5754) 2023-06-20 07:47:55 +00:00
Chang Liu 53f2c30942 [Feature] Decompose dataset to each process to add multi-node support for dataloader (#5617) 2023-06-20 07:43:05 +00:00
galogm 5945011d4c [Bugfix] dgl.linkx_homophily calculation fails when all class homophily=0 (#5720) 
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-06-20 07:43:05 +00:00
Chang Liu e6eefd1a13 [Bugfix] Fix the uninitialized pin_memory flag for empty graph (#5609) 2023-04-26 17:56:01 -07:00
Chang Liu 00c3edc1cf [Bugfix] Fix unit test failures on older GPUs (#5579) 2023-04-21 18:33:51 -07:00
Kunal Mukherjee c0f346e754 [Model] Implemented SubgraphX Explainer for Heterogeneous graph (#5530) 
Co-authored-by: kxm180046 <kxm180046@utdallas.edu>
Co-authored-by: Nick Baker <ndbaker1@outlook.com>
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-04-21 14:05:02 +08:00
czkkkkkk f41934df87 [Sparse] Add conversion between DGLGraph and SparseMatrix. (#5553) 2023-04-20 18:00:34 +08:00
Zhiteng Li b58416f76a [NN] Refine the API of GraphormerLayer (#5565) 
Co-authored-by: rudongyu <ru_dongyu@outlook.com>
 2023-04-19 16:36:25 +08:00
Kunal Mukherjee 95aaa4934a [Fix] np.float and np.int deprecated usage (#5563) 
Co-authored-by: kxm180046 <kxm180046@utdallas.edu>
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-04-17 18:48:03 +08:00
Kunal Mukherjee 23ef2ddd71 [Fix] np.asscalar deprecated usage (#5557) 
Co-authored-by: kxm180046 <kxm180046@utdallas.edu>
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-04-17 13:52:25 +08:00
czkkkkkk b57c56d9a1 [Sparse] Support broadcasting operators (#5544) 2023-04-15 10:36:12 +08:00
czkkkkkk 7c465d20fc [Sparse] Support spspdiv (#5541) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-04-14 16:46:51 +08:00
rudongyu bb1f8850e5 [NN] Refactor the Code Structure of GT (#5100) 2023-04-14 11:50:14 +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
czkkkkkk 893098888e [Sparse] Support spspmul (#5543) 2023-04-13 09:07:49 +08:00
peizhou001 4864a9f903 [Bug] Merge rather replace when find reverse eids (#5532) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-16-19.ap-northeast-1.compute.internal>
 2023-04-12 10:42:42 +08:00
Chang Liu 62b5f50a5c [Feature] Import PyTorch's pin_memory() method for DGL graph structure (#5366) 2023-04-10 19:21:32 -07:00
Tianqi Zhang (张天启) 27b008b9b1 [BugFix] Fix unstable behavior of beuteforce-sharemem KNN (#5515) 2023-04-10 22:26:10 +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
Ilia Taraban acb4eb7ecd [Feature] Add bfloat16 support for CPU (#5497) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-04-06 11:16:41 +02:00
Mufei Li a244de579c [Dataset] WisconsinDataset (#5520) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-36-188.ap-northeast-1.compute.internal>
 2023-04-04 16:44:26 +08:00
Mufei Li dd4c74ff32 [Dataset] CornellDataset and TexasDataset (#5513) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-36-188.ap-northeast-1.compute.internal>
 2023-04-03 16:16:37 +08:00
czkkkkkk 4463b3d6a5 [Sparse] Support strided tensor when calling old DGL APIs (#5506) 2023-03-31 23:18:55 +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
Mufei Li 2b5921e759 [Dataset] Actor (#5511) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-36-188.ap-northeast-1.compute.internal>
 2023-03-31 10:28:50 +08:00
Mufei Li 690f37bbe9 update (#5507) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-36-188.ap-northeast-1.compute.internal>
 2023-03-28 19:22:44 +08:00
Hongzhi (Steve), Chen 5b409bf7f5 Rename_test (#5487) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>
 2023-03-24 18:44:24 +08:00
Mufei Li 9e532e7def [Dataset] Chameleon (#5477) 
* update

* update

* update

* lint

* update

* CI

* lint

* update doc

---------

Co-authored-by: Ubuntu <ubuntu@ip-172-31-36-188.ap-northeast-1.compute.internal>
 2023-03-23 22:34:00 +08:00
ZhenyuLU_Heliodore 4534650f5f [Dataset] Add ZINC Dataset (#5428) 
* Update dgl.data.rst

* Add files via upload

* Add files via upload

* Add files via upload

* Update zinc.py

* Update dgl.data.rst

* Update test_data.py

* Add files via upload

* Update cluster.py

* Update pattern.py

* Update zinc.py

* Update zinc.py

* Update test_data.py

* lint

* fix

* fix path

* update test on label shape

---------

Co-authored-by: rudongyu <ru_dongyu@outlook.com>
 2023-03-22 18:04:41 +08:00
czkkkkkk 866c70dace [Sparse] Fix bugs in Diag format conversions (#5465) 2023-03-21 09:24:53 +08:00
Hongzhi (Steve), Chen 8a83027274 [Misc] Merge test utils. (#5440) 
* merge

* format

* rename

* sort

* sort

* update

* update

* update

* Update tests/utils/checks.py

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

---------

Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-03-20 15:32:45 +08:00
Daniil Sizov 87fb7ed05b [Config] Enable libxsmm by default for AVX cpu (#5165) 
* Enable AVX by default

* Fix linting errors

* Fix win64 build (libxsmm not linked)

Libxsmm on Win64 is not linked, should be disabled by default

* Fix clang format issues

* Change lower supported cpu version to LIBXSMM_X86_AVX2

Change lower supported cpu version to LIBXSMM_X86_AVX2 to address https://github.com/dmlc/dgl/issues/3459 issue

* Fix unit test

Remove assumption that libxsmm is enabled in the config by default (only true for intel CPUs with AVX2 instructions)

---------

Co-authored-by: Ubuntu <ubuntu@ip-172-31-15-137.us-west-2.compute.internal>
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
 2023-03-16 02:05:22 +08:00
czkkkkkk 92e383c3b8 [Sparse] Remove the Python DiagMatrix class (#5444) 
* [Sparse] Remove the Python DiagMatrix class

* Update

* Update

* update

* Update
 2023-03-15 18:17:52 +08:00