Commits · a85382b0ffaab196464734405f6c4ed8822f6e79 · OpenDAS / dgl

01 Nov, 2019 1 commit
- [doc] simple readability and style changes (#965) · a85382b0
  John Andrilla authored Nov 01, 2019
  
  a85382b0
30 Oct, 2019 1 commit

[Bug Fix] Fix package reliability bug of networkx (#949) · 82499e60

xiang song(charlie.song) authored Oct 30, 2019

* upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test for mxnet TAGCov

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

* reproduce the bug

* Fix concurrency bug reported at #755.
Also make test_shared_mem_store.py more deterministic.

* Update test_shared_mem_store.py

* Update dmlc/core

* networkx >= 2.4 will break our examples

* Update tutorials/requirements

* fix selfloop edges

* upd version

82499e60

29 Oct, 2019 2 commits
- [Cleanup] Change Byte to Bool for training masks (#954) · 98c1448b
  Jacob Stevens authored Oct 29, 2019
```
* Change Byte to Bool for training masks

* Check if module has Bool, otherwise use Byte
```
  98c1448b
- [Misc] Update README(s) (#962) · 86cf154b
  Mufei Li authored Oct 29, 2019
```
* Update

* Update
```
  86cf154b
28 Oct, 2019 1 commit
- [BUG] Fix #717 (#946) · a6d5a0cb
  Quan (Andy) Gan authored Oct 28, 2019
```
* [BUG] Fix #717

* fix mxnet test
```
  a6d5a0cb
26 Oct, 2019 1 commit
- [Model] Clean up for Cluster GCN (#940) · 421b05e7
  Mufei Li authored Oct 26, 2019
```
* Update

* Update

* Update

* Update

* Update

* Update

* Fix

* Fix
```
  421b05e7
25 Oct, 2019 3 commits
- [Model Zoo] AttentiveFP (#955) · 52c7ef49
  Mufei Li authored Oct 26, 2019
```
* Update

* Fix style

* Update

* Update

* Fix

* Update

* Update
```
  52c7ef49
- Update README.md (#916) · 43028f70
  Quan (Andy) Gan authored Oct 25, 2019
```
* Update README.md

* Update README.md
```
  43028f70
- [Chemistry] Hot fix (#953) · 4eba1ce2
  Mufei Li authored Oct 25, 2019
```
* Hot fix

* CI
```
  4eba1ce2
21 Oct, 2019 7 commits
- [Model Zoo] Refactor and Add Utils for Chemistry (#928) · 577cf2e6
  Mufei Li authored Oct 22, 2019
```
* Refactor

* Add note

* Update

* CI
```
  577cf2e6
- add KG statistics. (#931) · 0bf3b6dd
  Da Zheng authored Oct 21, 2019
```
* add KG statistics.

* add Freebase.

* fix link.
```
  0bf3b6dd
- Add more test to kvstore (#944) · 70ee4b5e
  Chao Ma authored Oct 21, 2019
  
  70ee4b5e
- Send any shape of tensor rather than matrix (#942) · ff9f67ee
  Chao Ma authored Oct 21, 2019
  
  ff9f67ee
- [Dataset] Migration for Chemistry Datasets (#926) · ae3102d3
  Mufei Li authored Oct 21, 2019
```
* Update

* Update
```
  ae3102d3
- [Model] Gated Graph Neural Network for bAbI tasks (#880) · c37076df
  Xiagkun Hu authored Oct 21, 2019
```
* rrn model and sudoku

* add README

* refine the code, add doc strings

* add sudoku solver

* add example for sudoku_solver

* ggnn example

* Rewrite README file

* fix typos
```
  c37076df
- Voice and tone updates for readability (#938) · 8d848655
  John Andrilla authored Oct 20, 2019
```
Simple editorial updates
```
  8d848655
18 Oct, 2019 1 commit
- [Doc] minor spelling updates (#935) · 9c095a72
  Aaron Markham authored Oct 18, 2019
```
* minor spelling updates

* Update docs/source/features/builtin.rst
```
  9c095a72
12 Oct, 2019 1 commit

[KG] Add RESCAL model to DGL-KGE (#923) · 02fb0581

Chao Ma authored Oct 12, 2019

* Add RESCAL model

* update

* update

* match acc

* update

* add README.md

* fix

02fb0581

11 Oct, 2019 3 commits

Fix bug of KG train.py script. (#922) · 20439e1c
xiang song(charlie.song) authored Oct 12, 2019
```
It cannot work when only mxnet backend is installed.
```
20439e1c

[KG] Update CI to cover Knowledge Graph (#913) · 93e3c49d

xiang song(charlie.song) authored Oct 11, 2019

* upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test for mxnet TAGCov

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

* reproduce the bug

* Fix concurrency bug reported at #755.
Also make test_shared_mem_store.py more deterministic.

* Update test_shared_mem_store.py

* Update dmlc/core

* Update Knowledge Graph CI with new Docker image

* Remove unused line_profierx

* Poke Jenkins

* Update test with exit code check and simplify docker

* Update Jenkinsfile to make app test a standalone stage

* Update kg_test

* Update Jenkinsfile

* Make some KG test parallel

* Update

* KG MXNet does not support ComplEx

* Update Jenkinsfile

* Update Jenkins file

* Change torch-1.2 to torch-1.2-cu92

* ci

* Update ubuntu_install_mxnet_cpu.sh

* Update ubuntu_install_mxnet_gpu.sh

* We only need to test train and eval script.
Delete some test code

93e3c49d

[KG] ComplEx score func for MXNet (#918) · bde75256

xiang song(charlie.song) authored Oct 11, 2019

* upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test for mxnet TAGCov

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

* reproduce the bug

* Fix concurrency bug reported at #755.
Also make test_shared_mem_store.py more deterministic.

* Update test_shared_mem_store.py

* Update dmlc/core

* Add complEx for mxnet

* ComplEx is ready for MXNet

bde75256

09 Oct, 2019 2 commits
- [KG] a little update on readme. (#914) · c26b1bae
  Da Zheng authored Oct 09, 2019
```
* update readme.

* Update README.md
```
  c26b1bae
- update the web link of d2l (#915) · fc1aa194
  Chao Ma authored Oct 09, 2019
  
  fc1aa194
08 Oct, 2019 5 commits

[Fix] Fix typo in KGE readme · 5eae8e05
Minjie Wang authored Oct 08, 2019

5eae8e05
[Doc] Fix hetero tutorial directory (#912) · 9d64927c
Quan (Andy) Gan authored Oct 08, 2019

9d64927c
minor docstring fix (#910) · a1cdc7a5
Quan (Andy) Gan authored Oct 08, 2019

a1cdc7a5
[Hetero][Tutorial] Heterograph tutorials (#878) · 3ee7e112
Quan (Andy) Gan authored Oct 08, 2019
```
* heterograph tutorial skeleton

* [WIP][Tutorial] Heterogeneous graph tutorial

* fix

* update
```
3ee7e112

[Bug fix] Fix concurrency bug reported at issue#755 (#823) · fd1b1474

xiang song(charlie.song) authored Oct 08, 2019

* upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test for mxnet TAGCov

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

* reproduce the bug

* Fix concurrency bug reported at #755.
Also make test_shared_mem_store.py more deterministic.

* Update test_shared_mem_store.py

* Update dmlc/core

fd1b1474

07 Oct, 2019 2 commits
- [Release] Fix Conda CMake flags (#907) · 5e17ef5d
  Quan (Andy) Gan authored Oct 07, 2019
```
* [Release] Fix CMake flags

* more fix
```
  5e17ef5d
- [Release] Bump conda version (#906) · 8c20c666
  Quan (Andy) Gan authored Oct 07, 2019
  
  8c20c666
06 Oct, 2019 4 commits
- [Windows] Working around a mysterious VS2015 error (#905) · 8c6cead2
  Quan (Andy) Gan authored Oct 07, 2019
  
  8c6cead2
- [Hetero] Doc (#892) · e2b7f745
  Mufei Li authored Oct 06, 2019
```
* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* style fixes & undefined name fix

* transpose=False in test
```
  e2b7f745
- extend warning to other adjacency_matrix() calls (#904) · b3d596b5
  Quan (Andy) Gan authored Oct 06, 2019
  
  b3d596b5
- [BUGFIX] check the number of columns in subgraph.copy_from_parent (#903) · bce51cbd
  Da Zheng authored Oct 05, 2019
```
* check the number of columns.

* add test.
```
  bce51cbd
04 Oct, 2019 2 commits
- [Doc] Update kg readme (#901) · 3a0bbb3e
  Da Zheng authored Oct 04, 2019
```
* add Freebase results.

* update.

* explain

* add DistMult.

* reproduce.
```
  3a0bbb3e
- [KG] save embeddings in NumPy (#900) · df8a7be5
  Da Zheng authored Oct 04, 2019
```
* fix loading and saving.

* use numpy.
```
  df8a7be5
03 Oct, 2019 3 commits
- use PBG sampler for testing. (#899) · 3bc31098
  Da Zheng authored Oct 02, 2019
  
  3bc31098
- fix (#898) · 251a9842
  Da Zheng authored Oct 02, 2019
  
  251a9842
- [Doc] Fix KG readme (#897) · 190cdbd2
  Da Zheng authored Oct 02, 2019
```
* fix.

* update readme.

* shorten format desc.
```
  190cdbd2
02 Oct, 2019 1 commit

[KG][Model] Knowledge graph embeddings (#888) · 15b951d4

Da Zheng authored Oct 02, 2019

* upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test for mxnet TAGCov

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

* init version.

* change default value of regularization.

* avoid specifying adversarial_temperature

* use default eval_interval.

* remove original model.

* remove optimizer.

* set default value of num_proc

* set default value of log_interval.

* don't need to set neg_sample_size_valid.

* remove unused code.

* use uni_weight by default.

* unify model.

* rename model.

* remove unnecessary data sampler.

* remove the code for checkpoint.

* fix eval.

* raise exception in invalid arguments.

* remove RowAdagrad.

* remove unsupported score function for now.

* Fix bugs of kg
Update README

* Update Readme for mxnet distmult

* Update README.md

* Update README.md

* revert changes on dmlc

* add tests.

* update CI.

* add tests script.

* reorder tests in CI.

* measure performance.

* add results on wn18

* remove some code.

* rename the training script.

* new results on TransE.

* remove --train.

* add format.

* fix.

* use EdgeSubgraph.

* create PBGNegEdgeSubgraph to simplify the code.

* fix test

* fix CI.

* run nose for unit tests.

* remove unused code in dataset.

* change argument to save embeddings.

* test training and eval scripts in CI.

* check Pytorch version.

* fix a minor problem in config.

* fix a minor bug.

* fix readme.

* Update README.md

* Update README.md

* Update README.md

15b951d4