* pickling support
* resorting to suggested way of pickling
* custom attribute pickling check
* working around a weird pytorch pickling bug
* including partial frame case
* pickling everything now
* fix as requested
* Fix
1. Fix two typos in gcn.py and gcn_spmv.py
2. Update README
* Fix GCN module
1. Update the outdated graph convolution layer class
2. Fix a bug in the code where dropout never works. Modules like dropout/batch norm depend on whether we are in the training stage or inference stage.
* Fix a bug in dropout
1. dropout depends on nn.Module.training
* Update GCN module
* Fix README
* Fix dropout & remove self.msg_field
* Fix
* Align with TF implementation
* Make g an argument for forward
* Remove features from the argument of GraphConv layer
* Support for create nodes/edges after setting representations
* Remove redundant commit
* Delete test_init_repr.py
* Test case for dynamic addition
* Base 'add_rows' upon 'append'
* Move test function
* Fix
* test by assertion
* changed add_rows to adding blank rows only; adding convert_to to backend
* moving test to basics
* oops mxnet
* support mxnet.
* add mxnet version of GCN.
* rename mxnet.nd as F.
* add mxnet GAT.
* enable GPU for GCN.
* fix MXNet GCN train.
* Use adam to optimize GAT
* support more operators.
* support sparse arrays.
* update mxnet backend.
* support index_copy.
* remove NN.
* update mxnet backend.
* temp check in.
* fix data conversion.
* add test.
* clean up mxnet backend.
* update mxnet examples.
* Revert "remove NN."
This reverts commit d815d9a0ec619f9ce9099c48cd35db9d8e947483.
* temp disable MXNet version of NN.
* WIP: API renaming
* API rewrite and node function refactor
* builtin functions
* builtin functions tested
* fix test
* send and recv spmv test
* WIP: fix examples
* Fix examples using new APIs
* subgraph copy from
* WIP
* cached members
* Change all usage of id tensor to the new Index object; remove set device in DGLGraph;
* subgraph merge API tested
* add dict type reduced msg test
* subgraph
* more test cases
* WIP
* new FrameRef and test
* separate nx init code
* WIP
* subgraph code and test
* line graph code and test
* adding new test for adding new features on line graphs
* no backtracking line graph
* fix inplace relabel
* model code for generative graphs
* batched version for dynamic graph generation using padding
* renaming function train back to forward
* remove old util function for padding DGMG
* override networkx clear to reset state, add dgl.nn
* Dynamic graph without batching
* use relative import path
* load dataset, pad batch
* bug fix
* experimental batch and unbatch
* dgmg batched version
* minor tweak
* move preprocessing padding into data loading
* batch graph test code
* minor
* batched graph class and test cases
* make dgl.nn.gcn a simple layer plus minor fix
* update dgmg model
* test forward using attribute field
* use frame append, minor changes
* moving networkx operations out of forward
* revert some changes
* remove structural immutability check
* fix edge list order problem in cached graph.
* minor fix
* fix bug in edge iter
* SPMV works
* gcn spmv on CPU
* change gcn style
* fix cached graph performance; fixed gcn dataset bug
* reorg dir
* non-batch spmv; partial update problem with shape change
* fix reorder problem; finish gcn-batch impl
* pop API
* GPU context
* add reduce_msg related api to dgl graph
* add reduce_sum, switch backend from numpy to pytorch
* update gat gcn to use reduce msg api
* remove reduce_sum
* add built-in reduce functions
Da Zheng