GitLab

* 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

* improve speed

* fix bugs

* upd reg test

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>

* 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

* 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>

* 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>

* fix a partition.

* add comments.

* 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.

* upd

* upd

* upd

* upd

* upd

* adjust batch size.

* fix for eval.py

* adjust parameters in distributed training.

* move code.

* compact

* prealloc memory for hashtable

* Fix

* upd

* Reduce memory

* upd
Co-authored-by: Ubuntu <ubuntu@ip-172-31-51-214.ec2.internal>

Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>

* 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

* patch

* fix+1

* add readme

* fix error message

* patch

* fix+1

* add readme

* patch

* fix+1

* 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.

Co-authored-by: Ubuntu <ubuntu@ip-172-31-60-78.ec2.internal>

* add metis.

* add test.

* construct partition id.

* link to METIS github repo.

* update metis.

* add a tool for partitioning a graph.

* update metis.

* update.

* update.

* fix metis.

* fix lint

* fix indent.

* another way of building metis.

* disable metis in windows.

* test windows

* fix.

* disable metis for windows properly.

* fix for tensorflow.

* skip test for gpu.

* make graph symmetric

* address comments.

* more comments.

* fix compile

* fix a bug.

* add test.

* change the default #hops of HALO nodes.
Co-authored-by: Ubuntu <ubuntu@ip-172-31-26-167.us-east-2.compute.internal>

* 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

* add num nodes in ctors

* fix

* lint

* addresses comments

* replace with constexpr

* remove function with rvalue reference

* address comments

* fix script

* t

* fix weird bugs

* fix

* fix

* upload

* fix

* fix

* lint

* fix

* tmp

* fix serialization

* fix

* fix lint

* fix message

* fix

* lint

* address comment

* fix

* lint

* fix

* fix

* fix

* Remove duplicate serialization for meta graph
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>

* Update README.md

* Update README.md

* Update README.md
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com>

* Fix RelGraphConv when num_bases is None

* Improve error message in when num_bases is wrong

* Fix integer modulo by zero exception when num_bases is 0
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com>

* fix

* data type

* fix

* fix

* fix

* automatically select nn backend

* rename load_backend to private

* switch to backend_name
Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com>

* 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>

This commit fixes a bug where the lock guard (for concurrently accessing
the same scope from different threads) had basically no effect, due to
being bound to a temporary only.
Co-authored-by: Minjie Wang <minjie.wang@nyu.edu>

* 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>

* fix.

* fix.

* fix.

* fix cmake.