ca2a7e1ca1
[Refactor] Nodeflow, sampling, CAPI ( #430 )
...
* 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
2019-03-05 14:07:22 -05:00
bea07b41b3
[Sampler] fix the API of neighbor sampler. ( #407 )
...
* don't return aux_info.
* fix sampler test.
* fix sse.
* fix.
* add comment.
2019-02-28 13:45:21 -08:00
7e30382e4f
[Model][MXNet] neighbor sampling & skip connection & control variate & graphsage ( #322 )
...
* 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
2019-02-28 13:29:51 -08:00
565f0c88fc
[WIP] [NN] Refactor NN package ( #406 )
...
* 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
2019-02-25 18:41:21 -05:00
f370e628cd
[Feature] add NodeFlow API ( #361 )
...
* sample layer subgraphs.
* fix.
* fix.
* add layered subgraph.
* fix lint.
* fix.
* fix tutorial.
* fix.
* remove copy_to_parent.
* add num_layers
* move sampling code to sampler.cc
* fix.
* move subgraph construction out.
* Revert "move subgraph construction out."
This reverts commit 24b3d13b0d8ed5f91847ea75a7674ee8f7d45cff.
* change to NodeFlow.
* use NodeFlow in Python.
* use NodeFlowIndex.
* add node_mapping and edge_mapping.
* remove unnecessary code in SSE tutorial.
* Revert "remove unnecessary code in SSE tutorial."
This reverts commit 093f0413d5fa2e63ca5f80c46c80a126a9fb720c.
* fix tutorial.
* move to node_flow.
* update gcn cv updater.
* import NodeFlow.
* update.
* add demo code for vanilla control variate sampler.
* update.
* update.
* add neighbor sampling.
* return flow offsets.
* update node_flow.
* add test.
* fix sampler.
* fix graph index.
* fix a bug in sampler.
* fix map_to_layer_nid and map_to_flow_eid.
* fix apply_flow.
* remove model code.
* implement flow_compute.
* fix a bug.
* reverse the csr physically.
* add mini-batch test.
* add mini batch test.
* update flow_compute.
* add prop_flows
* run on specific nodes.
* test copy
* fix a bug in creating frame in NodeFlow.
* add init gcn_cv_updater.
* fix a minor bug.
* fix gcn_cv_updater.
* fix a bug.
* fix a bug in NodeFlow.
* use new h in gcn_cv_updater.
* add layer_in_degree and layer_out_degree.
* fix gcn_cv_updater for gpu.
* temp fix in NodeFlow for diff context.
* allow enabling/disabling copy back.
* add with-updater option.
* fix a bug in computing degree.
* add with-cv option.
* rename and add comments.
* fix lint complain.
* fix lint.
* avoid assert.
* remove assert.
* fix.
* fix.
* fix.
* fix.
* fix the methods in NodeFlow.
* fix lint.
* update SSE.
* remove gcn_cv_updater.
* correct comments for the schedulers.
* update comment.
* add map_to_nodeflow_nid
* address comment.
* remove duplicated test.
* fix int.
* fix comments.
* fix lint
* fix.
* replace subgraph with NodeFlow.
* move view.
* address comments.
* fix lint.
* fix lint.
* remove static_cast.
* fix docstring.
* fix comments.
* break SampleSubgraph.
* move neighbor sampling to sampler.cc
* fix comments.
* rename.
* split neighbor_list.
* address comments.
* fix.
* remove TODO.
2019-02-19 15:49:28 -08:00
6c3dba867a
[Tutorial] Update prerequisites of README ( #380 )
...
* Update prerequisites of README
* dependencies for pytorch models
* dependencies for mxnet models
* minor
2019-02-11 22:58:17 -05:00
9cd0df7dde
[Doc] Update README in MXNet GCN. ( #373 )
...
* update readme.
* Revert "update readme."
This reverts commit cd5ea512059adadfcb22a615a2c42bba12f334a8.
* update.
2019-02-02 21:59:07 -08:00
ddc2faa547
[Bugfix] Fix gat residual bug ( #355 )
...
* fix gat residual bug
* fix the residual addition; output heads; add some shape notations;
* minor
* fix the output head average
* add requests package in requirement
2019-01-12 08:37:01 -05:00
efae0f97d8
[Model] Improve GAT models ( #348 )
...
* two better GAT implementations
* update numbers
* use version switch for spmm
* add missing dropout and output heads
2019-01-11 02:02:06 -05:00
1e50cd2eda
[Model][MXNet] MXNet Tree LSTM example ( #279 )
...
* TreeLSTM MXNet example
* hybridize
* add glove download
* usability
* Update README.md
2018-12-27 10:57:23 +08:00
896dc50e70
[Model] fix bugs in pygat and mxgat. ( #323 )
...
* mxgat
* pygat
* Update gat_batch.py
* add train
* Update gat_batch.py
* Update gat.py
* Update gat_batch.py
2018-12-23 20:45:25 -05:00
632d598c77
[Doc] Add readme to mxnet gat ( #300 )
...
* readme
* Update and rename README to README.md
* Update README.md
* Update README.md
* Update README.md
* Update README.md
* Update README.md
* Update README.md
* Update README.md
* Update README.md
2018-12-17 04:36:26 -08:00
f8811c7d3c
[BUGFIX] fix some minor problems in GAT ( #308 )
...
* fix gat.
* fix context.
2018-12-16 22:20:27 -08:00
dba36c87af
Fix some minor problems in SSE ( #309 )
...
* fix SSE.
* fix.
* fix.
2018-12-16 21:21:35 -08:00
f35ac5443e
[Graph][Model] Cache adj & inc; MX GCN ( #307 )
...
* add cache to adj and incmat
* Fix bug in cached adj/inc
* mx gcn spmv runnable; acc debugging...
* fix bug in mx gcn that loss is not correctly calculated
* fix mx utest
* fix as requested
* use raw parameter tensors rather than dense layer
* fix dropout
* Add numbers in readme
2018-12-16 22:51:01 -05:00
cffa4034f5
[Model] fix GCN ( #305 )
...
* mxnet gcn spmv
* update readme
* fix gcn
* pytorch gcn
* update readme
2018-12-16 12:44:41 -05:00
ac660f45ef
[Doc] Readme ( #265 )
...
* [Doc] updated readme
* contribution guide change
* small edits
* add perf #
* Update README.md
* Update README.md
* add others...
* rewrite scalability
* model & code links
* some note for treelstm
* rewrite scalability
2018-12-06 00:31:04 -05:00
f4a9a455f5
[Doc] Fix hyperlink in tutorial of tutorals ( #260 )
...
* fix all code tutorial links and typos in texts
* sse readme format
* fix
* sse paper link
* gat readme
* fix
2018-12-05 15:04:27 -05:00
e557ed89ff
[Doc][Model] example folder doc and model summary ( #259 )
...
* update example readme
* mx example readme
* add results in readme
* mx rgcn readme
2018-12-05 14:35:14 -05:00
2c5b48ab60
[Model][MXNet] RGCN Entity Classification ( #246 )
...
* entity classify work for examples
* add loop_msg
* remove wrong assert
* remove one reshape
* add readme
* add MRR
* remove mrr from entity task
2018-12-05 10:27:59 -08:00
7c7cc7e0c2
[sampler] Adjust the sampler API for the future extension. ( #243 )
...
* return seed ids.
* fix tests.
* implement.
2018-12-05 10:05:10 -08:00
a5a35d1f7a
[Sampler] improve random shuffle performance in sampler ( #228 )
...
* fix.
* make it generic.
* add the API.
* fix.
* remove mxnet.
2018-12-04 09:24:32 -08:00
78269cedfd
[Doc] Update GCN README.md ( #224 )
...
* update readme.
* update readme
2018-12-04 12:07:05 -05:00
2c170a8c17
[Graph][Bugfix] Fix the API of map_to_subgraph_nid ( #226 )
...
* correct vid mapping API.
* fix sse.
2018-12-03 17:16:35 -05:00
6f4898a128
[Model][MXNet] gcn normalization and compare with mlp baselines ( #196 )
...
* clean up pr-188 and resubmit
* address Da comments
2018-12-02 19:17:37 -08:00
57b07fce92
[Model] Accelerate SSE ( #172 )
...
* lazy eval edge ids.
* parallelize node id lookup.
* fix a bug.
* use mxnet for index.
* use update_all in the subgraph training.
* sample neighbors.
* Revert "parallelize node id lookup."
This reverts commit e661f69bb06cb5a7c246f0e106f245e27800e220.
* update README.
* cache subgraphs.
* support all degrees.
* cache adj in CPU.
* fix a bug in sse.
* print.
* raise error on mutable graphs.
* measure train time per epoch.
* fix a bug in graph_index.
* remove readonly in DGLSubGraph.
* cache subgraph properly.
* accelerate getting adjacency.
* split infer.
* lazy eval edges.
* specify inference mode.
* update for new sampler.
* use new mxnet sampling api.
* fix indent.
* remove profiling code.
* remove mxnet from sampler.
* return a lambda function for graph edges.
* add docs for immutable subgraph.
* Revert "return a lambda function for graph edges."
This reverts commit 0de5d7f100e230c518a3fb8976a6227f474d09ee.
* get parent_eid.
2018-12-02 12:43:25 -05:00
02eb463ab1
report accuracy and fix training mask ( #181 )
2018-11-27 15:15:57 +08:00
5f89cd662e
Fix the convergence problem in SSE. ( #162 )
...
* add a test.
* move file.
* debug
* add degree normalization.
* it can converge now.
* remove hidden_data.
* use readonly graph index.
* use subgraph loader.
* refactor code and remove intermediate data.
* split inference.
* mix cpu and gpu training.
* fix mxnet sparse_matrix constructor.
* convert tensor context.
* set up the prediction model.
* load mxnet csr directly.
* add timing.
* move test_sse.py to sse_batch.py
* fix the tensor version of SSE.
* update README.
2018-11-20 15:57:52 +08:00
2389df8155
[API] Subgraph sampling API. ( #138 )
...
* add neighbor sampler.
* fix sampler.
* handle non-existing nodes differently in MapParentIdToSubgraphId.
* fix sampling tests.
* parallelize sampling.
* add more tests.
* fix a bug in subgraph loader.
* get number of sampled nodes directly.
* load mxnet CSR to DGLGraph directly.
* create graph from mxnet csr array directly.
* use subgraph loader in SSE.
* fix a bug in sampling.
* output framework tensor.
* fix.
* remove unnecessary code.
* fix tests.
* add SSE README.
* move to contrib.
* address comments.
* add tests.
2018-11-14 13:51:27 -08:00
bd0e4fa0b3
[MXNet][API] move to the new API ( #123 )
...
* move gat to the new api.
* fix gcn.
* update sse.
* fix dgl core.
* update sse.
* fix small bugs in dgl core.
* fix mxnet tests.
* retrigger
* address comments and fix more bugs.
* fix
* fix tests.
2018-11-08 10:00:47 -08:00
9e9a9488f1
[GraphIndex] Immutable graph index using MXNet CSRArray ( #86 )
...
* 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.
2018-10-26 11:28:25 -07:00
5567f4a4d9
[BACKEND] Add MXNet backend. ( #77 )
...
* 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.
2018-10-14 11:15:48 -04:00
15a2c22c98
Reorg folders; basic impl of the APIs
2018-06-14 21:37:43 -04:00
Minjie Wang