GitLab

* add C++ rpc infrastructure and distributed sampler

* update

* update lint

* update lint

* update lint

* update

* update

* update

* updare

* update

* update

* update

* update serialize and unittest

* update serialize

* lint

* update

* update

* update

* update

* update

* update

* update unittest

* put Finalize() to __del__

* update unittest

* update

* delete buffer in Finalize

* update unittest

* update unittest

* update unittest

* update unittest

* update

* update

* fix small bug

* windows socket impl

* update API

* fix bug in serialize

* fix bug in serialzie

* set parent graph

* update

* update

* update

* update

* update

* update

* fix lint

* fix lint

* fix

* fix windows compilation error

* fix windows error

* change API to lower-case

* update test

* fix typo

* update

* add SamplerPool

* add SamplerPool

* update

* update test

* update

* update

* update

* update

* add example

* update

* update

* random walk traces generation

* remove outdated comments

* oops put in the wrong place

* explicit inline

* moving rand_r to util

* pinsage-like model on movielens

* the code runs now

* support cuda

* using readonly graph

* moving random walk to public function

* per-thread seed and openmp support

* pinsage-like model on movielens

* the code runs now

* support cuda

* using readonly graph

* using C random walk

* removing profile decorators

* param initialization

* no grad

* leaky relu fixes everything

* train and save

* WIP

* WIP

* WIP

* seems to work

* evaluation output

* swapping order of val/test and train

* debug

* hyperparam tuning

* prior/training dataset split changes

* random walk reorg

* random walk with restart

* signed comparison fix

* migrating random walk to nodeflow

* Revert "migrating random walk to nodeflow"

This reverts commit f2565347cced7c912a58a529b257c033d9f375b7.

* add README and remove dataset

* new endpoint

* lint

* lint x2

* oops forgot test

* including bpr - better for baseline

* addressing fixes

* throwing random walks out from SamplerOp class

* forgot to move RandomWalk; why did this even work?

* removing legacy garbage

* add todo

* address comments

* stupid bug fix

* call ndarrayvector converter to handle traces

* forgot prefetch switch

* yet another stupid bug

* fix bug in pickling

* fix lint

* fix performance bug in EdgeSoftmax

* minor

* refactored sampler code

* docstring

* fix tutorial

* fix send with builtin bug

* test cases

* remove todo comment

* fix rgcn tutorial

* small fix

* upd

* findedge/s

* upd

* upd

* upd

* upd

* add test

* remove redundancy

* upd

* upd

* upd

* upd

* add edge_subgraph

* explicit cast

* add test immutable subg

* reformat

* reformat

* fix bug

* upd

* hotfix

* subgraph docs

* fix adj mat

* fix edges() order

* add test

* revert

* upd

* fix

* upd

* update README performance number

* news

* fix cython bug

* fix

* fix

* update version

* update news

* refactor.

* accelerate update_all in nodeflow.

* fix.

* refactor.

* fix lint.

* fix lint.

* reorganize.

* reorg.

* remove.

* add doc.

* impl block_incidence_matrix

* fix lint.

* fix.

* simple fix.

* fix test.

* fix interface.

* fix eid.

* fix comments.

* enable cython

* add helper function and data structure for void_p vector return

* move sampler from graph index to contrib.sampling

* WIP

* WIP

* refactor layer sampling

* pass tests

* fix lint

* fix graphsage

* remove comments

* pickle test

* fix comments

* update dev guide for cython build

* use index_select instead of __getitem__

* fix bug in dataset processing

* fix edge_type shape bug

* comments

* migrate to node-flow

* uniform layer sampler test cases

* more test cases

* documentations

* fix lint errors

* fix lint errors

* fix lint errors

* iota

* add asnumpy

* requested changes

* fix indptr error

* fix lint errors

* requested changes & fix lint errors

* fix lint errors

* fix LayerSampler unit test

* implement pytorch spmm with gather and scatter add

* fix

* replace torch take with index_select

* comments

* comment about pytorch __getitem__ operator pitfall

* typo

* fix rgcn tutorial

* small fix

* upd

* findedge/s

* upd

* upd

* upd

* upd

* add test

* remove redundancy

* upd

* upd

* upd

* upd

* add edge_subgraph

* explicit cast

* add test immutable subg

* reformat

* reformat

* fix bug

* upd

* hotfix

* subgraph docs

* don't return aux_info.

* fix sampler test.

* fix sse.

* fix.

* add comment.

* neighbor sampling draft

* val/test acc

* control variate draft

* control variate

* update

* fix new_history

* maintain aggregated history while updating new history

* preprocess the first layer, change push to pull

* update

* fix subg_degree

* nodeflow

* clear

* readme

* doc and unittest for self loop

* address comments

* rename

* update

* fix

* Update node_flow.py

* Update node_flow.py

* fix rgcn tutorial

* small fix

* upd

* findedge/s

* upd

* upd

* upd

* upd

* add test

* remove redundancy

* upd

* upd

* upd

* upd

* add edge_subgraph

* explicit cast

* add test immutable subg

* reformat

* reformat

* fix bug

* upd

[Bugfix] Removing non-determinism in data loading

* refactor graph conv

* docs & tests

* fix lint

* fix lint

* fix lint

* fix lint script

* fix lint

* Update

* Style fix

* Fix style

* Fix style

* Fix gpu case

* Fix for gpu case

* Hotfix edgesoftmax docs

* Handle repeated features

* Add docstring

* Set default arguments

* Remove dropout from nn.conv

* Fix

* add util fn for renaming

* revert gcn_spmv.py

* mx folder

* fix wierd bug

* fix mx

* fix lint

* simple implemention of GraphSAGE

* update the abstract method and `torch.nn` modules are more utilized

* [Model] Simplifying Graph Convolutional Networks.

* - improve code stype (use nn.Linear)
- use `bias` option
- update hyperparameter and corresponding performance

* 9_gat.py

* readme

* Update 9_gat.py

* Update 9_gat.py

* fix format

* fix rgcn tutorial

* small fix

* add switch readonly state interface

* remove trailing ws

* fix

* fix

* change signature

* change signature

* remove trailing ws

* upd

* upd interface

* upd

* rm trailing ws

* reformat

* trailing space

* upd

* fix.

* add check.

* fix assert.

* random walk traces generation

* remove outdated comments

* oops put in the wrong place

* explicit inline

* moving rand_r to util

* moving random walk to public function

* per-thread seed and openmp support

* type cast styles