GitLab

* upd

* upd

* upd

* upd

* upd

* passed test

* add note

* upd

* trigger

* slight change

* upd

* upd

* trigger

* fix

* simplify

* upd

* upd

* fudge

* upd

* trigger

* test partial

* upd

* trigger

* DGMG for molecule generation

* Fix CI check

* Fix for CI

* Trial for CI due to shared memory

* Update

* Better interface for dataset configuration

* Update

* Handle corner cases

* Update README

* Fix

* Fix

* Fix

* Fix

* Fix

* Refactor

* Fix

* Fix

* Fix

* Fix

* Fix

* Fix

* Update

* Fix

* Fix

* Fix

* Fix

* Fix

* Finallly

* 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

* rgcn module

* support id input

* WIP: model codes

* use faster index select

* dropout

* self loop

* WIP: link prediction

* fix lint

* WIP: docs

* docstring

* docstring

* merge two child classes

* mxnet rgcn module

* fix lint

* fix lint

* fix rename bug

* add uniform edge sampler

* fix fn name

* docstring

* fix mxnet rgcn module

* fix mx rgcn

* enable test on cuda

* moving heterograph index to another file

* node view

* python interfaces

* heterograph init

* bug fixes

* docstring for readonly

* more docstring

* unit tests & lint

* oops

* oops x2

* removed node/edge addition

* addressed comments

* lint

* rw on frames with one node/edge type

* homograph with underlying heterograph demo

* view is not necessary

* bugfix

* replace

* scheduler, builtins not working yet

* moving bipartite.h to header

* moving back bipartite to bipartite.h

* oops

* asbits and copyto for bipartite

* tested update_all and send_and_recv

* lightweight node & edge type retrieval

* oops

* sorry

* removing obsolete code

* oops

* lint

* various bug fixes & more tests

* UDF tests

* multiple type number_of_nodes and number_of_edges

* docstring fixes

* more tests

* going for dict in initialization

* lint

* updated api as per discussions

* lint

* bug

* bugfix

* moving back bipartite impl to cc

* note on views

* fix

* add edge sampler.

* add test and run.

* add negative sampling.

* remap the edge subgraph vid.

* negative graph excludes edges of positive edgs.

* remove print.

* avoid sampling NodeFlow when expand_factor or num_hops is 0.

* fix a bug when excluding nodes in negative graph.

* support multigraph.

* exclude positive edges.

* fix memory leak.

* return subgraph object directly.

* fix many problems.

* add comments.

* address comments

* 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 early stop

* add mxnet version

* Poke ci

* csr interface

* csr wrapper for immutable graph

* lint

* silly fix

* docstring

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+.

* [Model zoo] Model zoo (#765)

* tox21

* fix ci

* fix ci

* fix urls to url

* add doc

* remove binary

* model zoo

* test

* markdown

* fix typo

* fix typo

* fix typo

* raise error

* fix lint

* remove unnecessary

* fix doc

* fix

* fix

* fix

* fix

* fix

* fix

* Update

* CI

* Fix

* Fix

* Fix

* Fix

* Fix

* CI

* tox21

* fix ci

* fix ci

* fix urls to url

* add doc

* remove binary

* upd

* fig edgebatch edges

* add test

* trigger

* rrn model and sudoku

* add README

* refine the code, add doc strings

* add sudoku solver

* [Model] SchNet

* [Model] SchNet model

* [Model] Schnet Model fix device-related bug

* [Model] SchNet fix bugs

* [Model] SchNet fix some bugs

* [Model] Schnet 🎨 code indent format

* [Model] SchNet ✏ fix some typos

* fix NDArray reference

* fix lint

* capture NDArray in the closure

* nonuniform sampler

* unit test

* test on out neighbors

* error checks

* lint

* fix

* clarification

* use macro switcher

* use empty array for uniform sampling

* oops

* Revert "oops"

This reverts commit a11f9ae707aaeb67fb5921c887a17d3711d5b04a.

* Revert "use empty array for uniform sampling"

This reverts commit 8526ce4cade89f2c1b09a08aca8830375ebafb31.

* re-reverting

* use a method

* removal doc

* glob

* upd

* rm knn

* add softmax

* upd

* upd

* add broadcast and s2s

* optimize max_on

* forsaken changes to heterograph

* upd

* upd

* upd

* upd

* upd

* bugfix

* upd

* upd

* upd

* upd

* format upd

* upd format

* upd doc

* upd

* import order

* upd

* rm warnings

* fix

* upd test

* upd

* upd

* fix device

* upd

* upd

* upd

* upd

* remove 1.1

* upd

* trigger

* trigger

* add more tests

* fix device

* upd

* upd

* refactor

* fix?

* fix

* upd docstring

* refactor

* upd

* fix

* upd

* upd

* upd

* fix

* upd docs

* add shape

* refactor & upd doc

* upd doc

* upd

* Refactoring Communicator

* fix lint

* change non-const reference

* add header file

* use MemoryBuffer

* update PR

* fix bug on csr shape

* zero-copy msg_queue

* fix lint

* fix lint

* fix lint

* add header file

* fix windows build error

* fix windows build error

* update

* fix lint

* update

* fix lint

* fix lint

* add more test

* fix windows test

* update windows test

* update windows test

* update windows test

* update

* fix lint

* fix lint

* update

* update

* update

* update

* use STATUS code

* update test

* remove mem_cpy

* fix lint

* update

* finish

* ConstructNFTensor

* add test for deallocator

* update

* fix lint

* add local scope function

* fix lint

* fix docstring

* change local_scope to local_var; add context manager

* address comments

* rng refactor

* fix bugs

* unit test

* remove setsize

* lint

* fix test

* use explicit instantiation instead of inlining

* stricter test

* use tvm solution

* moved python interface to dgl.random

* lint

* address comments

* make getthreadid an inline function

* return 1 option in scipy adjacency matrix

* lint

* use dgl warning

* i'm an idiot

* lint x2

* rename

* finish bipartite graph implementation; compiled

* finished heterograph implementation; compiled

* WIP: apis

* C API codes

* compiled

* WIP: python

* HeteroGraphIndex

* WIP: test

* add DGLContext support in ffi

* fix bug in has edge

* unittests except edge subgraph

* edge subgraph

* fix lint

* address comments

* poke ci

* try fix

* fix msvc

* WIP: using object system for graph

* c++ side refactoring done; compiled

* remove stale apis

* fix bug in DGLGraphCreate; passed test_graph.py

* fix bug in python modify; passed utest for pytorch/cpu

* fix lint

* address comments

* WIP: array refactoring

* WIP: implementation

* wip

* most csr part

* WIP: on coo

* WIP: coo

* finish refactoring immutable graph

* compiled

* fix undefined ndarray copy bug; add COOToCSR when coo has no data array

* fix bug in COOToCSR

* fix bug in CSR constructor

* fix bug in in_edges(vid)

* fix OutEdges bug

* pass test_graph

* pass test_graph

* fix bug in CSR constructor

* fix bug in CSR constructor

* fix bug in CSR constructor

* fix stupid bug

* pass gpu test

* remove debug printout

* fix lint

* rm biparate grpah

* fix lint

* address comments

* fix bug in Clone

* cpp utests

* try venv for win64

* update

* update

* trying another

* update

* update

* update

* trigger ci

* update

* update

* formatting

* formatting

* WIP: import tvm runtime node system

* WIP: object system

* containers

* tested basic container composition

* tested custom object

* fix setattr bug

* tested object container return

* fix lint

* some comments about get/set state

* fix lint

* fix lint

* update cython

* fix cython

* ffi doc

* fix doc

* diffpool original file added

* make diffpool fuse up and running

* minor tweak on tu dataset statistics method

* fix tu

* break

* delete break

* pre_org

* diffpool fuse reorg

* fix random shuffling

* fix bn

* add dgl layers

* early stopping

* add readme

* fix

* add diffpool preprocess script

* tweak tu dataset

* tweak

* tweak

* tweak

* tweak

* tweak

* preprocess dataset

* fix early stopping

* fix

* fix

* fix

* tweak

* readme

* code review

* code review

* dataset code review

* update README

* code review

* tu doc