* WIP: TypedLinear and new RelGraphConv
* wip
* further simplify RGCN
* a bunch of tweak for performance; add basic cpu support
* update on segmm
* wip: segment.cu
* new backward kernel works
* fix a bunch of bugs in kernel; leave idx_a for future
* add nn test for typed_linear
* rgcn nn test
* bugfix in corner case; update RGCN README
* doc
* fix cpp lint
* fix lint
* fix ut
* wip: hgtconv; presorted flag for rgcn
* hgt code and ut; WIP: some fix on reorder graph
* better typed linear init
* fix ut
* fix lint; add docstring
1. Update `examples/pytorch/gcn` and `python/dgl/nn/pytorch` based on the latest APIs
2. Add full support for dropout in `examples/pytorch/gcn` and `python/dgl/nn/pytorch`
3. Rename `GCN` class in `python/dgl/nn/pytorch` to be `GraphConvolutionLayer` class
4. Make node field an argument that can be configured by users in GraphConvolutionLayer
Note that adjacency normalization has not been supported yet in the examples.
* 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
rudongyu