GitLab

* add immutable graph index.

* update ImmutableGraphIndex.

* add benchmarks of subgraph generation.

* fix node_subgraphs.

* use scipy synthetic data in immutable graph.

* create immutable_graph.

* use spmv in gcn.

* fix immutable graph index.

* update graph index.

* create ImmutableSubgraphIndex.

* return subgraph node and edge mapping.

* fix benchmark.

* add mapping to subgraph nid.

* test in_edges and out_edges.

* update benchmark.

* Fix immutable subgraph.

* complete in_edges and out_edges.

* fix benchmarks.

* add test on node_subgraphs

* add sse.

* construct subgraphs in parallel.

* add in/out degree(s).

* make immutable graph index backend-specific.

* implement has_edge(s) and edge_id(s).

* Revert "use spmv in gcn."

This reverts commit 9cfed5f5fb3dd2ed9b98745348b1c0e9731ed7f7.

* implement node_subgraphs in GraphIndex.

* fix sse.

* address comments.

* address comments.

* Update mxnet docker.

* fix tests.

* enable mxnet CI.

* add mxnet tests.

* update jenkins.

* update mxnet docker image.

* fixing networkx conversion with 0 edges

* fixes as required

* remove obsolete comment

* gcn example test code

* GPU test

* use python3

* use functions

* gpu test use functions

* remove root

* use one script to run both cpu and gpu tests

* update mxnet.

* add get_tvmtype.

* remove undefined test.

* refactor frame codes

* fix unit test

* fix gcn example

* minor doc/message changes

* raise errors for non-exist columns in FrameRef; sanity check when append

* fix unittest; change error msg

* Add warning for none initializer

* fix unittest

* use warnings package

[Hotfix] Revert part of the send logic; disable the send twice test case; GCN on GPU works again. (#88)

* multigraph support on graph index

* more tests

* multigraph flag, bugfix on clear & copy

* networkx interfaces

* including graph index tests in Jenkins

* node subgraph test

* edge subgraphs

* removing duplicates in pred/succ

* more explicit test and doc

* query source and destination from edge id

* subgraphindex

* renaming has_edge to has_edge_between, apply_edges adding eid

* send_on and send_and_recv_on

* DGLGraph edge subgraph

* merged send_on and send_and_recv_on

* change request

* removing hashmap

* creating multigraph by flag; mingw support

* changes per request

* reverting networkx auto multigraph discovery

* notes on send/send_and_recv on multigraphs

* changing test reducer from sum to max

* added a fixme note in spmv scheduler

* node/edge filtering

* changing to tensor operations (what did i do???)

* ???

* 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.

* Test CPP branch CI (#2)

* Fix batching node-only graphs (#62)

* fixing batching with graphs with no edges

* oops forgot test

* fix readme

* Docker and Jenkins (#1)

* docker ci cpu

* install python packages

* docker ci gpu

* add readme

* use dgl cpu image

* run command in container as root

* use python3

* fix test case

* remove nose from docker file

* docker folder readme

* parallelize cpu and gpu

* top level stages

* comment out python2 related installation

* fix

* remove igraph

* building for cpp

* change building order

* export env in test stage

* withEnv

* run docker container as root

* fix test cases

* fix test cases

* minor

* remove old build

* update subgraph.

* update subgraph API.

* keep node embedding.

* fixing batching with graphs with no edges

* oops forgot test

* support multiple fields in spmv

* finishing SPMV executor

* non-spmv case

* refactor code to give single mfunc rfunc a shortcut

* two test cases to test multiple msg/red func

* catching cases where msg uses anonymous field

* default ALL for update edge

* more corner case test

* print failed test

* delete print

* fix builtin max reducer

* 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

* WIP

* WIP

* treelstm dataloader

* Main training loop.

* trainable treelstm script

* fix dependency

* cuda training

* Add tensorized topological traversal

* allowing update_to() with no incoming messages

* fixing partial cases

* fixing 0 degree reduces

* adopting accum=None semantics

* minor fix as per reviews

* TODO in test

* fix test

* fix dgl.batch edge ordering bug

* add graph batching test cases

* fix partial spmv ctx.

* add dataset generating for dgmg

* 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

* partial spmv impl and test

* some fix for update edge

* GAT model

* fix output projection to have only one head