项目文件夹

文件

T

文件历史

xiang song(charlie.song) e17add5602 [NN] Add MXNet impl for TAGCN module. (#799 )

* upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

2019-08-28 13:19:17 +08:00

appnp

[Refactor] Interface of nn modules (#798 )

2019-08-27 22:29:25 +08:00

capsule

all demo use python-3 (#555 )

2019-05-23 10:38:05 +08:00

dgi

all demo use python-3 (#555 )

2019-05-23 10:38:05 +08:00

dgmg

all demo use python-3 (#555 )

2019-05-23 10:38:05 +08:00

diffpool

[Model][Hotfix] DiffPool formatting fix (#696 )

2019-07-02 15:19:57 +08:00

gat

[Refactor] Interface of nn modules (#798 )

2019-08-27 22:29:25 +08:00

gcn

[Refactor] Interface of nn modules (#798 )

2019-08-27 22:29:25 +08:00

gin

[Refactor] Interface of nn modules (#798 )

2019-08-27 22:29:25 +08:00

graphsage

[Refactor] Interface of nn modules (#798 )

2019-08-27 22:29:25 +08:00

jtnn

[Model zoo] JTNN model zoo (#790 )

2019-08-28 04:04:54 +08:00

line_graph

all demo use python-3 (#555 )

2019-05-23 10:38:05 +08:00

model_zoo

[Model Zoo] GAT on Tox21 (#793 )

2019-08-28 04:47:16 +08:00

pointcloud

[NN] Renaming NearestNeighborGraph to KNNGraph (#802 )

2019-08-28 12:20:35 +08:00

recommendation

[Doc] Update README.md for pytorch PinSage example. (#770 )

2019-08-16 02:23:05 -03:00

rgcn

[NN] RGCN modules (#744 )

2019-08-23 16:38:48 -04:00

rrn

[Model] Recurrent Relational Network (RRN) on sudoku (#733 )

2019-08-10 02:00:11 +08:00

sampling

[Doc] Update README.MD of demo for distributed sampler (#579 )

2019-05-30 01:24:13 -04:00

sgc

[Refactor] Interface of nn modules (#798 )

2019-08-27 22:29:25 +08:00

tagcn

[NN] Add MXNet impl for TAGCN module. (#799 )

2019-08-28 13:19:17 +08:00

transformer

all demo use python-3 (#555 )

2019-05-23 10:38:05 +08:00

tree_lstm

all demo use python-3 (#555 )

2019-05-23 10:38:05 +08:00

pagerank.py

[API][Doc] API change & basic tutorials (#113 )

2018-11-02 17:19:14 -04:00

README.md

[README] Update speed numbers in README (#661 )

2019-06-15 14:27:58 -07:00

README.md

Model Examples using DGL (w/ Pytorch backend)

Each model is hosted in their own folders. Please read their README.md to see how to run them.

To understand step-by-step how these models are implemented in DGL. Check out our tutorials

Model summary

Here is a summary of the model accuracy and training speed. Our testbed is Amazon EC2 p3.2x instance (w/ V100 GPU).

Model	Reported Accuracy	DGL Accuracy	Author's training speed (epoch time)	DGL speed (epoch time)	Improvement
GCN	81.5%	81.0%	0.0051s (TF)	0.0031s	1.64x
GAT	83.0%	83.9%	0.0982s (TF)	0.0113s	8.69x
SGC	81.0%	81.9%	n/a	0.0008s	n/a
TreeLSTM	51.0%	51.72%	14.02s (DyNet)	3.18s	4.3x
R-GCN (classification)	73.23%	73.53%	0.2853s (Theano)	0.0075s	38.2x
R-GCN (link prediction)	0.158	0.151	2.204s (TF)	0.453s	4.86x
JTNN	96.44%	96.44%	1826s (Pytorch)	743s	2.5x
LGNN	94%	94%	n/a	1.45s	n/a
DGMG	84%	90%	n/a	238s	n/a