GitLab

* Edit for grammar and style

Improve readability

* Update tutorials/models/1_gnn/README.txt
Co-Authored-By: Aaron Markham <markhama@amazon.com>

* Update tutorials/models/1_gnn/README.txt
Co-Authored-By: Aaron Markham <markhama@amazon.com>

* Edit for grammar and style

Improve the flow and readability

* Update docs/source/features/nn.rst

Better now? NN Modules as a title is vague

* grammatical updates

Edit pass for readability. 
Can you clarify: "are of different, but shapes that can be broadcast." Are they of different shapes, but both can be broadcast?

* Update docs/source/features/builtin.rst

Okay now? Check this for logic.

* Edit for grammar and style

As with other tutorials, it would help the reader if you add a paragraph in the opening section about assumptions or prerequisites.

Does this refer to SageMaker Ground Truth feature? "...assigns its ground truth label..." If yes, phrase it thus: assigns its Amazon SageMaker Ground Truth label

* Update tutorials/basics/4_batch.py

* Update tutorials/basics/4_batch.py

* Update tutorials/basics/4_batch.py

topologies

* Update tutorials/basics/4_batch.py
Co-Authored-By: Aaron Markham <markhama@amazon.com>

* Grammar and style edit pass

In the opening, it would be great to provide some rationale for why you recommend conda or pip.

* Update docs/source/install/index.rst
Co-Authored-By: Aaron Markham <markhama@amazon.com>

* Update docs/source/install/index.rst
Co-Authored-By: Aaron Markham <markhama@amazon.com>

* Update docs/source/install/index.rst
Co-Authored-By: Aaron Markham <markhama@amazon.com>

fix minor error: GCNLayerSAGE->GraphSAGELayer

* Update

* Update

* Update

* Fix

* CI style fix

* CI fix style

* Fix

* Try CI

* Fix test

* Update

* Update

* Update

* Update

* [Example] Finish adaptive sampling

* refactor code and use argparse for command-line usage

* Update README.md

* add node_per_layer command-line argument

* Update

* Try CI

* Edit for readability

Edit pass for grammar and style. 
* A great value-add would be to provide assumptions and prerequisites in the opening section. This helps readers understand what they need to have in place in order to make use of your tutorial steps.
* The wikidata knowledge graph could be improved with a smaller font for the Zuckerberg circle.

* Update tutorials/hetero/1_basics.py

* Update tutorials/hetero/1_basics.py
Co-Authored-By: Aaron Markham <markhama@amazon.com>

* Update tutorials/hetero/1_basics.py
Co-Authored-By: Aaron Markham <markhama@amazon.com>

* Update tutorials/hetero/1_basics.py
Co-Authored-By: Aaron Markham <markhama@amazon.com>

* Update tutorials/hetero/1_basics.py
Co-Authored-By: Aaron Markham <markhama@amazon.com>

* Update tutorials/hetero/1_basics.py
Co-Authored-By: Aaron Markham <markhama@amazon.com>

Can you add a link for the download to this sentence: You can also `download <location?>` and run the different code examples...
As with other tutorial topics, it would be helpful to add your assumptions or information in the opening section about prerequisites.

* Edit for grammar and style

In the opening paragraph, it would be helpful to provide some overall scenario and the prerequisites you expect readers to have completed before they start here. "This tutorial assumes you have already..." Add a link to Install DGL topic perhaps and any other framework or IDE or even specialized knowledge. With this context, you help readers to succeed by setting expectations.

Better to group all tutorials (this, PageRank with, Batched Graph, Working with) at the same level in the left navigation rail and all as subsections of DGL Basics.

* Update tutorials/basics/2_basics.py

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

* Small change for kvstore api

* fix ci

* fix ci

* Performance improvment for distributed kvstore

* update

* update

* 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

* 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

* 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

* Change Byte to Bool for training masks

* Check if module has Bool, otherwise use Byte

* Update

* Update

* [BUG] Fix #717

* fix mxnet test

* Update

* Update

* Update

* Update

* Update

* Update

* Fix

* Fix

* Update

* Fix style

* Update

* Update

* Fix

* Update

* Update

* Update README.md

* Update README.md

* Hot fix

* CI

* Refactor

* Add note

* Update

* CI

* add KG statistics.

* add Freebase.

* fix link.

* Update

* Update

* 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