GitLab

* 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

* update metis

* update

* update dataloader

* update dataloader

* new script

* update

* update

* update

* update

* update

* update

* update

* update dataloader

* update

* update

* update

* update

* update

Co-authored-by: Chao Ma <mctt90@gmail.com>

* partition a KG.

* get tid.

* support builtin

* fix a minor bug.
Co-authored-by: Chao Ma <mctt90@gmail.com>

* adjust batch size.

* fix for eval.py

* adjust parameters in distributed training.

* move code.

* 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

* Now dataset accepts user define datasets

* UPdate README

* Fix eval

* Fix

* Fix Freebase

* Fix

* Fix

* upd

* upd

* Update README

* Update some docstrings.

* upd
Co-authored-by: Ubuntu <ubuntu@ip-172-31-8-26.us-east-2.compute.internal>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-19-78.us-east-2.compute.internal>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-60-78.ec2.internal>

* save config.

* save more.

* 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>

* update

* change name

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* change worker number

* update

* update

* update

* update

* update

* update

* test

* update

* update

* update

* remove barrier

* max_step

* update

* add complex

* update

* chmod +x

* update

* update

* random partition

* random partition

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* change num_test_proc

* update num_thread

* update

* Several optimizations on DGL-KG:
1. Sorted positive edges for sampling which can reduce random
   memory access during positive sampling
2. Asynchronous node embedding update
3. Balanced Relation Partition that gives balanced number of
   edges in each partition. When there is no cross partition
   relation, relation embedding can be pin into GPU memory
4. tunable neg_sample_size instead of fixed neg_sample_size

* Fix test

* Fix test and eval.py

* Now TransR is OK

* Fix single GPU with mix_cpu_gpu

* Add app tests

* Fix test script

* fix mxnet

* Fix sample

* Add docstrings

* Fix

* Default value for num_workers

* Add soft relation part

* Upd

* Some fix

* upd

* Now work

* Fix TransR

* Fix eval and add some doc string

* triger

* upd

* Add some training scripts for freebase multi-gpu

* upd

* upd

* upd

* Several optimizations on DGL-KG:
1. Sorted positive edges for sampling which can reduce random
   memory access during positive sampling
2. Asynchronous node embedding update
3. Balanced Relation Partition that gives balanced number of
   edges in each partition. When there is no cross partition
   relation, relation embedding can be pin into GPU memory
4. tunable neg_sample_size instead of fixed neg_sample_size

* Fix test

* Fix test and eval.py

* Now TransR is OK

* Fix single GPU with mix_cpu_gpu

* Add app tests

* Fix test script

* fix mxnet

* Fix sample

* Add docstrings

* Fix

* Default value for num_workers

* Upd

* upd

* remote copy from parent

* upd

* make test_sampler easier to pass

* multi-gpu

* Pytorch can run but test has acc problem

* pytorch train/eval can run in multi-gpu

* Fix eval

* Fix

* Fix mxnet

* trigger

* triger

* Fix mxnet score_func

* Fix

* check

* FIx default arg

* Fix train_mxnet mix_cpu_gpu

* Make relation mix_cpu_gpu

* delete some dead code

* some opt for update

* Fix cpu grad update

* attach positive.

* add neg_deg_sample.

* add comment.

* add neg_deg_sample for eval.

* change the edge sampler.

* rename edge sampler in KG.

* allow specifying chunk size and negative sample size separately.

* fix bugs in KG.

* add check in sampler.

* add more checks.

* fix

* add comment.

* add comments.

* remove parallel sampling for multiprocessing.

* avoid memory copy in eval.

* remove print.

* add no_eval_filter

* fix eval.

* accel edge sampling.

* measure sampling time.

* attach positive.

* add neg_deg_sample.

* fix a minor bug.

* remove unnecessary code.

* Revert "add neg_deg_sample."

This reverts commit 45f3c08c87e33589563ca7e6a3ec91cb1239910e.

* Revert "attach positive."

This reverts commit 503d7821555b69b7ccfed55ce8b87ee24fff852d.
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com>

* reduce memory consumption.

* fix a bug.

* fix a bug.

* fix.

* Add weight based edge sampler

* Can run, edge weight work.
TODO: test node weight

* Fix node weight sample

* Fix y

* Update doc

* Fix syntex

* Fix

* Fix GPU test for sampler

* Fix test

* Fix

* Refactor EdgeSampler to act as class object not function that it
can record its own private states.

* clean

* Fix

* Fix

* Fix run bug on kg app

* update

* update test

* test

* Simply python API and fix some C code

* Fix

* Fix

* Fix syntex

* Fix

* Update API description

* add replacement for edge sampler

* Now edge sampler support replacement and no-replacement

* Fix

* Fix

* change kg/app to use edge sampler with replacement config

* Update replacement algo

* Fix syntax

* Update

* Update
Co-authored-by: Da Zheng <zhengda1936@gmail.com>

* 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

* Add L2 distance score for TransE

* Update README.md

* Use linalg.gemm to speedup mx l2 dist

* Fix

Add RotatE support for KGE (apps/kg)
Performance Result:
Dataset FB15k:
Result from Paper:
MR: 40
MRR: 0.797
HIT@1: 74.6
HIT@3: 83.0
HIT@10: 88.4

Our Impl:
MR: 39.6
MRR: 0.725
HIT@1: 62.8
HIT@3: 80.2
HIT@10: 87.5

* Add TransR for kge

* Now Pytorch TransR can run

* Add MXNet TransR

* Now mxnet can work with small dim size

* Add test

* Pass simple test_score

* Update test with transR score func

* Update RESCAL MXNet

* Add missing funcs

* Update init func for transR score

* Revert "Update init func for transR score"

This reverts commit 0798bb886095e7581f6675da5343376844ce45b9.

* Update score func of TransR MXNet

Make it more memory friendly and faster,
thourgh it is still very slow and memory consuming

* Update best config

* Fix ramdom seed for test

* Init score-func specific var

* Update Readme

* add KG statistics.

* add Freebase.

* fix link.

* Add RESCAL model

* update

* update

* match acc

* update

* add README.md

* fix

It cannot work when only mxnet backend is installed.

* 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

* 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

* update readme.

* Update README.md

* add Freebase results.

* update.

* explain

* add DistMult.

* reproduce.

* fix loading and saving.

* use numpy.