ff244df0ea
post-release
2020-04-06 22:31:51 +08:00
0ee95a5e73
Update ( #1419 )
2020-04-04 01:22:16 +08:00
b94d3da84f
[Docs] Fix doc build doesn't work for nn.tensorflow and nn.mxnet ( #1413 ) ( #1417 )
...
* fix
* lint
* fix
2020-04-03 20:33:54 +08:00
e1d90f9b5e
update version
2020-03-30 16:21:04 +00:00
8a061d1ce1
update version
2020-03-30 16:14:46 +00:00
4a281ff3e6
Merge branch 'master' into 0.4.x
2020-03-30 16:14:14 +00:00
e4cc81852d
[Windows] fix compilation issues on vs2015 ( #1405 )
...
* [Windows] fix compilation issues on vs2015
* fix test
2020-03-30 22:08:26 +08:00
e9440acb06
[TF] TF backend fix and new logic to choose backend ( #1393 )
...
* TF backend fix and new logic to choose backend
* fix
* fix
* fix
* fix
* fix backend
* fix
* dlpack alignment
* add flag
* flag
* lint
* lint
* remove unused
* several fixes
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2020-03-30 18:45:17 +08:00
4b4186f87d
[Sampler] Change argument type of fanout from list to dict ( #1403 )
2020-03-30 15:52:46 +08:00
97b08fbba5
[BUG] fix crash in neighbor sampling w/ replacement on 0 degree nodes ( #1402 )
2020-03-30 14:48:23 +08:00
e3a9a6bba8
add an optional include_dst_in_src argument ( #1401 )
2020-03-30 12:06:12 +08:00
af61e2fbb4
[Feature] Support nn modules for bipartite graphs. ( #1392 )
...
* init gat
* fix
* gin
* 7 nn modules
* rename & lint
* upd
* upd
* fix lint
* upd test
* upd
* lint
* shape check
* upd
* lint
* address comments
* update tensorflow
Co-authored-by: Quan Gan <coin2028@hotmail.com >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2020-03-29 16:48:38 +08:00
67cb7a43a0
[Feature] Deprecate multigraph ( #1389 )
...
* Deprecate multi-graph
* Handle heterograph and edge_ids
* lint
* Fix
* Remove multigraph in C++ end
* Fix lint
* Add some test and fix something
* Fix
* Fix
* upd
* Fix some test case
* Fix
* Fix
Co-authored-by: Ubuntu <ubuntu@ip-172-31-51-214.ec2.internal >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2020-03-28 21:31:24 +08:00
3efb5d8ecf
[NN] Add HeteroGraphConv module for cleaner module definition ( #1385 )
...
* Add HeteroGraphConv
* add custom aggregator; some docstring
* debugging
* rm print
* fix some acc bugs
* fix initialization problem in weight basis
* passed tests
* lint
* fix graphconv flag; add error message
* add mxnet heteroconv
* more fix for mx
* lint
* fix torch cuda test
* fix mx test_nn
* add exhaust test for graphconv
* add tf heteroconv
* fix comment
2020-03-27 18:47:06 +08:00
bbfff8ce76
[Feature] Casting between DGLGraph and DGLHeteroGraph ( #1391 )
...
* [Feature] Casting between DGLGraph and DGLHeteroGraph
* lint
* address comments
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2020-03-27 13:34:55 +08:00
ebda932d2f
[CI] Tensorflow ci ( #1397 )
...
* fix
* fix
2020-03-27 03:35:24 +08:00
1e27e90e4e
[MXNet] Patch mxnet unittest ( #1395 )
...
* patch
* turn off tf test
* skip test
* fix
2020-03-26 01:05:59 +08:00
08fcda325b
[Doc] Fix link to backends docs ( #1376 )
...
Co-authored-by: Tong He <hetong007@gmail.com >
2020-03-25 18:20:09 +08:00
b9c65e91ef
[BUG] Another fix on remove edges when all edges are removed ( #1386 )
...
* [BUG] Another fix on remove edges when all edges are removed
* fix mxnet
2020-03-23 19:04:52 +08:00
d27b485912
[BUG] Fix remove_edges crashing with empty edge ID tensors ( #1384 )
2020-03-22 21:09:44 +08:00
a0721405cf
[BUGFIX] don’t import dgl in the package. ( #1382 )
...
* fix dgl data.
* remove more.
* fix.
* fix.
Co-authored-by: Ubuntu <ubuntu@ip-172-31-16-150.us-west-2.compute.internal >
2020-03-22 01:29:16 -07:00
10253a5c07
[BUGFIX] Fix is_multigraph in the construction from scipy coo matrix ( #1357 )
...
* fix is_multigraph in from_coo.
* add tests for partition.
* fix.
* Revert "add tests for partition."
This reverts commit cb8c8555da3e0c70a482c2d639adce2943475bfc.
* fix everywhere from_scipy_sparse_matrix is used.
2020-03-22 00:30:27 -07:00
856de790e8
Update README
...
Update README with both latest and stable doc links
2020-03-22 10:44:16 +08:00
2cdc4d3c1d
[Doc] Patch tutorial ( #1380 )
...
* patched 1_first
* done 2_basics
* done 4_batch
* done 1_gcn, 9_gat, 2_capsule
* 4_rgcn.py
* revert
* more fix
2020-03-22 10:21:22 +08:00
0f40c6e49c
[Hetero] Replace card with num_nodes
...
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2020-03-20 16:56:53 +08:00
1b9bc16b1a
[KG]Update README and config ( #1375 )
...
* Update README and config
* upd
Co-authored-by: Ubuntu <ubuntu@ip-172-31-60-78.ec2.internal >
2020-03-19 17:06:02 +08:00
4af02022b2
[Bug] Multiple fixes ( #1374 )
...
* multiple fixes
* lint
* lint x2
2020-03-19 11:19:44 +08:00
0a51dc5435
[Bug] Fix dsttype in GraphSAGE minibatch model ( #1371 )
...
* fix for new ntype API for blocks
* adding two new interfaces
2020-03-18 23:57:03 +08:00
635dfb4a59
[DGL-KE] Add license to every file header ( #1368 )
...
* update metis
* update
* update dataloader
* update dataloader
* new script
* update
* update
* update
* update
* update
* update
* update
* update dataloader
* update
* update
* update
* update
* update
* update
* update
* Add license to every filer header
2020-03-17 17:46:18 +08:00
f8ae6350b1
[DGL-KE] Add METIS preprocessing pipeline ( #1365 )
...
* update metis
* update
* update dataloader
* update dataloader
* new script
* update
* update
* update
* update
* update
* update
* update
* update dataloader
* update
* update
* update
* update
* update
2020-03-17 17:15:04 +08:00
2ce0e21b6b
Update ( #1366 )
2020-03-16 22:00:19 +08:00
166275754c
Update instructions for building from source ( #1363 )
...
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2020-03-16 19:38:36 +08:00
6111ea4665
[Model] RGCN mini-batch training; Better bipartite graph support ( #1337 )
...
* change the model to use node embedding only
* minibatch training
* add readme
* small fix
* backward-compatible
* backward compatible
* modify to_block; rgcn changed
* fix
* fix transform
* fix bug in unittest script
* docstring
* fix lint
* add tests
* address comments; fix offline eval
* gitignore
2020-03-16 18:58:06 +08:00
9120ee60a5
Update README.md
2020-03-15 23:47:58 +08:00
d876680a36
[Model][Perf] Improve sage sampling performance ( #1364 )
...
* improve speed
* fix bugs
* upd reg test
2020-03-15 23:20:30 +08:00
f9ad1c80da
fix. ( #1358 )
...
Co-authored-by: Chao Ma <mctt90@gmail.com >
2020-03-15 12:23:32 +08:00
eb71c804e8
[KG] partition a KG. ( #1351 )
...
* partition a KG.
* get tid.
* support builtin
* fix a minor bug.
Co-authored-by: Chao Ma <mctt90@gmail.com >
2020-03-15 11:53:44 +08:00
545cc065c0
[DGL-LifeSci] WLN for Reaction Center Prediction ( #1360 )
...
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Update
2020-03-14 13:13:38 +08:00
5a1ef70fd4
[Optimization] Optimize performance of COOSort ( #1349 )
...
* Fix coo_sort
* Add COOSort test
* Fix
* omp
* coo2csr can benefit from sorted coo
* Add more test code
* Add LIBCXX_ENABLE_PARALLEL_ALGORITHMS to Makefile
* upd
* Turn off LIBCXX_ENABLE_PARALLEL_ALGORITHMS by default
Co-authored-by: Ubuntu <ubuntu@ip-172-31-51-214.ec2.internal >
2020-03-13 22:39:36 +08:00
f3b866f4eb
Update ( #1359 )
2020-03-13 17:38:57 +08:00
6c7c403914
[Feature] Filtered MRR metrics for R-GCN example ( #1298 )
...
* Add filtered metrics for R-GCN example
* Add new line to end of file
* Add evaluation protocol argument option for R-GCN example
* Update README
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com >
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com >
Co-authored-by: Ubuntu <ubuntu@ip-172-31-51-214.ec2.internal >
2020-03-13 16:25:03 +08:00
87842db48e
Fix for dataloader ( #1353 )
2020-03-12 19:09:46 +08:00
3938b399d9
[BUGFIX] metis partition should generate a subgraph to the original graph. ( #1352 )
...
* fix a partition.
* add comments.
2020-03-12 10:43:08 +08:00
1a584ced11
[Feature] Improve the speed of to_bidirected ( #1327 )
...
* make graph symmetric
* call gklib routine.
* use gklib version except in windows.
* minor errors.
* fix test.
* update doc.
* fix a compile error.
* fix.
* add comments for the new C API.
* fix a bug.
* address comments.
* fix compile error.
* fix comment.
2020-03-10 22:44:32 -07:00
9432cd63ca
fix sampler. ( #1350 )
2020-03-11 11:01:03 +08:00
988c8b20a4
[DOC] Improve the docstring of GATConv and new APIs ( #1339 )
...
* upd
* upd
* upd
* upd
* upd
2020-03-11 01:14:22 +08:00
e65840434b
[KG] make batch size compatible with neg sample size ( #1343 )
...
* adjust batch size.
* fix for eval.py
* adjust parameters in distributed training.
* move code.
2020-03-10 01:14:33 -07:00
7b3a7b1438
[Optimization] Optimize CompactGraph ( #1328 )
...
* compact
* prealloc memory for hashtable
* Fix
* upd
* Reduce memory
* upd
Co-authored-by: Ubuntu <ubuntu@ip-172-31-51-214.ec2.internal >
2020-03-10 12:54:12 +08:00
20e1bb455b
rewrite to use dataloader ( #1333 )
...
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2020-03-10 09:22:41 +08:00
d98c71ef90
[DGL-KE] Clean up argument for DGL-KE ( #1325 )
...
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* clean up args
* change args for eval
* update
* update
* update
* update num_worker=8
* add num_proc=1
* update
* update
* add eval percent
* update
* update
* update
* save emb
* update
* update
* update
* update
* update
* remove neg_chunk_size
* update
* update
* update
* remove
* update
* remove
* change num_thread
2020-03-09 23:11:56 +08:00
Quan Gan