9de930bb25
Update README.md
2020-07-17 23:21:28 +08:00
7c47d8c9b4
[Feature] Simplify shared memory graph index ( #1381 )
...
* simplify shared memory graph index.
* fix.
* remove edge_dir in SharedMemGraphStore.
* avoid creating shared-mem graph store with from_csr.
* simplify from_csr.
* add comments.
* fix lint.
* remove the test.
* fix compilation error.
* fix a bug.
* fix a bug.
Co-authored-by: Ubuntu <ubuntu@ip-172-31-16-150.us-west-2.compute.internal >
2020-04-05 15:33:47 -07:00
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
0f40c6e49c
[Hetero] Replace card with num_nodes
...
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2020-03-20 16:56:53 +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
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
d876680a36
[Model][Perf] Improve sage sampling performance ( #1364 )
...
* improve speed
* fix bugs
* upd reg test
2020-03-15 23:20:30 +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
20e1bb455b
rewrite to use dataloader ( #1333 )
...
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com >
2020-03-10 09:22:41 +08:00
a9520f71ce
[Model][Sampler] GraphSAGE model, bipartite graph conversion & remove edges API ( #1297 )
...
* remove edge and to bipartite and graphsage with sampling
* fixes
* fixes
* fixes
* reenable multigpu training
* fixes
* compatibility in DGLGraph
* rename to compact_as_bipartite
* bugfix
* lint
* add offline inference
* skip GPU tests
* fix
* addresses comments
* fix
* fix
* fix
* more tests
* more docs and unit tests
* workaround for empty slice on empty data
2020-03-08 02:38:29 +08:00
4ec8f204dd
Update ( #1319 )
2020-03-05 22:58:29 +08:00
93ac29ce34
[Refactor] Unify DGLGraph, BatchedDGLGraph and DGLSubGraph ( #1216 )
...
* upd
* upd
* upd
* lint
* fix
* fix test
* fix
* fix
* upd
* upd
* upd
* upd
* upd
* upd
* upd
* upd
* upd
* upd
* upd tutorial
* upd
* upd
* fix kg
* upd doc organization
* refresh test
* upd
* refactor doc
* fix lint
Co-authored-by: Minjie Wang <minjie.wang@nyu.edu >
2020-03-05 18:03:57 +08:00
cbee427839
[Model] Scene Graph Extraction Model with GluonCV ( #1260 )
...
* add working scripts
* add frcnn training script
* remove redundent files
* refactor validation computation, will optimize sgdet and training
* validation finally finished
* f-rcnn training
* test reldn
* rm file
* update reldn training
* data preprocess to h5
* temp
* use coco json
* fix conflict
* new obj dataset for detection
* update training
* before cleanup
* remove abundant files
* add arg parse to train
* cleanup code file
* update
* fix
* add readme
* add ipynb as demo
* add demo pic
* update readme
* add demo script
* improve paths
* improve readme
* add docstrings
* fix args description
* update readme
* add models from s3
* update README
Co-authored-by: Minjie Wang <minjie.wang@nyu.edu >
2020-03-05 11:54:26 +08:00
c23a61bd5c
fix s3 link ( #1310 )
2020-03-04 21:01:29 +08:00
b05cb84a77
[BUG] Fixes #1262 ( #1286 )
2020-02-24 13:33:55 +08:00
ddf8c858e1
[KVStore] Small fix on kvstore ( #1284 )
...
* update
* str to int
* update
* update
* update
* test remove sync
* update
* update
* update
* update
* update
* update
* update
* update
* clear
2020-02-23 15:43:34 +08:00
b133abb82e
[KVStore] New kvstore used by DGL-KE ( #1263 )
...
* new kvstore
* 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
* test warning
* update
* update
* udpate
* update
* update
* update
* update
* small fix
* small fix
* get group count
* update
* update
* make file
* update
* use addr
* get id
* partition book
* update
* partition
* barrier
* update
* loop count
* update
* update
* update
* update
* update
* update
* update
* update
* update
* add mxnet demo
* update ip
* update
* update
* update
* random
* update
* update
* update
* update
* update
* update
* fix lint
* fix lint
* fix lint
2020-02-17 13:39:13 +08:00
7a80faf120
[Bugfix] Correct the loss function in RGCN model ( #1217 )
...
* upd
* upd
* fix
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com >
2020-02-13 18:35:07 +08:00
3f0c10058a
[DGL-LifeSci] Fix broken links ( #1248 )
...
* Fix
* Update
2020-02-08 18:42:51 +08:00
77ae4d5321
[Example] Fix Rgcn hetero nonedetermistic in graph and model initialization ( #1244 )
...
* Fix model save and load problem.
Add offline inference example
* Fix test
* Fix randomness problem between test runs
* Make rdf loader deterministic
2020-02-07 11:07:09 +08:00
828a5e5bc6
[DGL-LifeSci] Migration and Refactor ( #1226 )
...
* First commit
* Update
* Update splitters
* Update
* Update
* Update
* Update
* Update
* Update
* Migrate ACNN
* Fix
* Fix
* Update
* Update
* Update
* Update
* Update
* Update
* Finish classification
* Update
* Fix
* Update
* Update
* Update
* Fix
* Fix
* Fix
* Update
* Update
* Update
* trigger CI
* Fix CI
* Update
* Update
* Update
* Add default values
* Rename
* Update deprecation message
2020-02-04 01:38:09 +08:00
a9dabcc769
[Feature] Random Walk for 0.5 ( #1209 )
...
* trying to refactor IndexSelect
* partial implementation
* add index select and assign for floats as well
* move to random choice source
* more updates
* fixes
* fixes
* more fixes
* adding python impl
* fixes
* unit test
* lint
* lint x2
* lint x3
* update metapath2vec
* debugging performance
* still debugging for performance
* tuning
* switching to succvec
* redo
* revert non-uniform sampler to use vector
* still not fast
* why does this crash with OpenMP???
* because there was a data race!!!
* add documentations and remove assign op
* lint
* lint x2
* lol what have i done
* lint x3
* fix and disable gpu testing
* bugfix
* generic random walk
* reorg the random walk source code
* Update randomwalks.h
* Update randomwalks_cpu.cc
* rename file
* move internal function to anonymous ns
* reorg & docstrings
* constant restart probability
* docstring fix
* more commit
* random walk with restart, tested
* some fixes
* switch to using NDArray for choice
* massive fix & docstring
* lint x?
* lint x??
* fix
* export symbols
* skip gpu test
* addresses comments
* replaces another VecToIdArray
* add randomwalks.h to include
* replace void * with template
2020-01-31 19:52:08 +08:00
a00636a02b
[Tensorflow] Several nn & example ( #1191 )
...
* several nn example
* appnp
* fix lint
* lint
* add dgi
* fix
* fix
* fix
* fff
* docs
* 111
* fix
* change init
* change result
* tiaocan+1
* fix
* fix lint
* fix
* fix
2020-01-19 22:48:40 +08:00
3d6646288f
Update README.md ( #1184 )
2020-01-09 12:06:48 +08:00
bfc2d3030d
[BUG] Fix MovieLens feature assignment ( #1183 )
...
Fixes #1182 .
This is embarrassing.
2020-01-09 11:21:18 +08:00
e705118bcc
some comments ( #1132 )
2020-01-06 10:36:11 +08:00
6731ea3af7
[KVStore] Reduce memory cost of kvstore ( #1156 )
...
* API change of kvstore
* add demo for kvstore
* update
* remove duplicated log
* change queue size
* update
* update
* update
* update
* update
* update
* update
* update
* update
* fix lint
* change name
* update
* fix lint
* update
* update
* update
* update
* change message queue size to a python argument
* change default queue size to 2GB
* OMP_NUM_THREADS=1
* add multiple NICs support for kvstore
* test
* fix lint
* update
* update
* update
* update
* update
* update
* update
* fix lint
* fix lint
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* fix lint
2019-12-30 20:25:32 +08:00
4f02bb751b
[KVStore] Made kvstore can support multiple NICs ( #1150 )
...
* API change of kvstore
* add demo for kvstore
* update
* remove duplicated log
* change queue size
* update
* update
* update
* update
* update
* update
* update
* update
* update
* fix lint
* change name
* update
* fix lint
* update
* update
* update
* update
* change message queue size to a python argument
* change default queue size to 2GB
* OMP_NUM_THREADS=1
* add multiple NICs support for kvstore
* test
* fix lint
* update
* update
* update
* update
* update
* update
* update
* fix lint
* fix lint
* update
* update
* update
* update
2019-12-30 15:17:31 +08:00
d57ff78da1
[Small Fix] Change default message queue size of communicator to 2GB ( #1140 )
...
* API change of kvstore
* add demo for kvstore
* update
* remove duplicated log
* change queue size
* update
* update
* update
* update
* update
* update
* update
* update
* update
* fix lint
* change name
* update
* fix lint
* update
* update
* update
* update
* change message queue size to a python argument
* change default queue size to 2GB
* OMP_NUM_THREADS=1
2019-12-25 17:03:52 +08:00
e4ef8d1a80
[KVStore] API change of kvstore ( #1058 )
...
* API change of kvstore
* add demo for kvstore
* update
* remove duplicated log
* change queue size
* update
* update
* update
* update
* update
* update
* update
* update
* update
* fix lint
* change name
* update
* fix lint
* update
* update
* update
* update
* change message queue size to a python argument
2019-12-24 17:05:15 +08:00
2ab4d0e10f
[Doc] Hotfix for README ( #1119 )
2019-12-23 19:22:38 +08:00
d30a69bf27
[Backend] TF backend ( #978 )
...
* tf
* add builtin support
* fiix
* pytest
* fix
* fix
* fix some bugs
* fix selecting
* fix todo
* fix test
* fix test fail in tf
* fix
* fix
* fix gather row
* fix gather row
* log backend
* fix gather row
* fix gather row
* fix for pytorch
* fix
* fix
* fix
* fix
* fix
* fix tests
* fix
* fix
* fix
* fix
* fix
* fix
* fix convert
* fix
* fix
* fix
* fix inplace
* add alignment setting
* add debug option
* Revert "add alignment setting"
This reverts commit ec63fb3506ea84fff7d447a1fbdfd1d5d1fb6110.
* tf ci
* fix lint
* fix lint
* add tfdlpack
* fix type
* add env
* fix backend
* fix
* fix tests
* remove one_hot
* remove comment
* remove comment
* fix
* use pip to install all
* fix test
* fix base
* fix
* fix
* add skip
* upgrade cmake
* change version
* change ci
* fix
* fix
* fix
* fix
* fix seg fault
* fix
* fix python version
* fix
* try fix
* fix
* fix
* tf takes longer time in ci
* change py version
* fix
* fix
* fix oom
* change kg env
* change kg env
* 啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊啊
* 我再也不搞各种乱七八糟环境了……
* use pytest
* Chang image
2019-12-20 15:56:51 +08:00
cf9ba90fd4
[Chem] ACNN and various utilities ( #1117 )
...
* Add several splitting methods
* Update
* Update
* Update
* Update
* Update
* Fix
* Update
* Update
* Update
* Update
* Fix
* Fix
* Fix
* Fix
* Fix
* Update
* Update
* Update
* Update
* Update
* Update
* Update
* Finally
* CI
2019-12-19 11:54:40 +08:00
2448751c8e
Fixed the training file ( #1109 )
2019-12-14 18:20:05 +08:00
d16fb3ff9d
[Example] GCMC in PyTorch ( #1101 )
...
* upd
* fix
* upd
* upd
* upd
* fix
* upd
* upd
* upd
* upd
* upd
* upd
* upd
* upd
2019-12-14 08:18:48 +08:00
bc4f4352d1
[Chem Model Zoo] Hot fix for README ( #1071 )
...
* Fix outdated example
* Hot fix
2019-12-05 14:37:06 +08:00
fff3dd9593
[Example] add graphwriter pytorch example ( #1068 )
...
* upd
* fig edgebatch edges
* add test
* trigger
* add graphwriter pytorch example
* fix line break in graphwriter README
* upd
* fix
2019-12-05 02:44:15 +08:00
fdc58a8996
[Hotfix] Fix GAT example and clarify the usage of early stop ( #1065 )
...
* upd
* rm redundancy:
* upd
2019-11-30 23:43:15 +08:00
dca2580b84
fix minor error: GCNLayerSAGE->GraphSAGELayer ( #1010 )
...
fix minor error: GCNLayerSAGE->GraphSAGELayer
2019-11-27 01:54:56 +08:00
85c9ff01c9
[Example] Finish adaptive sampling ( #998 )
...
* [Example] Finish adaptive sampling
* refactor code and use argparse for command-line usage
* Update README.md
* add node_per_layer command-line argument
2019-11-26 13:47:26 +08:00
1915fdb984
Make print of GCN example of mxnet and pytorch exact same. ( #994 )
2019-11-13 12:47:06 +08:00
a0193fd539
Small change for kvstore api ( #981 )
...
* Small change for kvstore api
* fix ci
* fix ci
2019-11-08 16:25:12 +08:00
7897fa3b9c
add init api on kvserver ( #975 )
2019-11-05 16:21:35 +08:00
cccde032f4
[kvstore] Performance improvement for distributed kvstore ( #972 )
...
* Performance improvment for distributed kvstore
* update
* update
2019-11-04 18:27:00 +08:00
fdd0fe651d
hotfix ( #971 )
2019-11-04 12:11:53 +08:00
9a0511c8e9
[NN] nn modules & examples update ( #890 )
...
* upd
* damn it
* fuck
* fuck pylint
* fudge
* remove some comments about MXNet
* upd
* upd
* damn it
* damn it
* fuck
* fuck
* upd
* upd
* pylint bastard
* upd
* upd
* upd
* upd
* upd
* upd
* upd
* upd
* upd
2019-11-03 17:29:42 -05:00
82499e602b
[Bug Fix] Fix package reliability bug of networkx ( #949 )
...
* 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
2019-10-29 23:34:31 -04:00
98c1448bfc
[Cleanup] Change Byte to Bool for training masks ( #954 )
...
* Change Byte to Bool for training masks
* Check if module has Bool, otherwise use Byte
2019-10-29 17:14:08 -04:00
86cf154be9
[Misc] Update README(s) ( #962 )
...
* Update
* Update
2019-10-29 15:37:25 +08:00
Mufei Li