Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
dgl
Commits
32e0f748
Commit
32e0f748
authored
Mar 08, 2019
by
Lingfan Yu
Committed by
Minjie Wang
Mar 08, 2019
Browse files
[Release] Update readme performance number (#441)
* update README performance number * news
parent
2ade0ef9
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
8 additions
and
3 deletions
+8
-3
README.md
README.md
+8
-3
No files found.
README.md
View file @
32e0f748
...
@@ -15,11 +15,11 @@ A summary of the model accuracy and training speed with the Pytorch backend (on
...
@@ -15,11 +15,11 @@ A summary of the model accuracy and training speed with the Pytorch backend (on
| Model | Reported
<br>
Accuracy | DGL
<br>
Accuracy | Author's training speed (epoch time) | DGL speed (epoch time) | Improvement |
| Model | Reported
<br>
Accuracy | DGL
<br>
Accuracy | Author's training speed (epoch time) | DGL speed (epoch time) | Improvement |
| ----- | ----------------- | ------------ | ------------------------------------ | ---------------------- | ----------- |
| ----- | ----------------- | ------------ | ------------------------------------ | ---------------------- | ----------- |
|
[
GCN
](
https://arxiv.org/abs/1609.02907
)
| 81.5% | 81.0% |
[
0.0051s (TF)
](
https://github.com/tkipf/gcn
)
| 0.00
42
s | 1.
17
x |
|
[
GCN
](
https://arxiv.org/abs/1609.02907
)
| 81.5% | 81.0% |
[
0.0051s (TF)
](
https://github.com/tkipf/gcn
)
| 0.00
38
s | 1.
34
x |
|
[
SGC
](
https://arxiv.org/abs/1902.07153
)
| 81.0% | 81.9% | n/a | 0.0008s | n/a |
|
[
SGC
](
https://arxiv.org/abs/1902.07153
)
| 81.0% | 81.9% | n/a | 0.0008s | n/a |
|
[
TreeLSTM
](
http://arxiv.org/abs/1503.00075
)
| 51.0% | 51.72% |
[
14.02s (DyNet)
](
https://github.com/clab/dynet/tree/master/examples/treelstm
)
| 3.18s | 4.3x |
|
[
TreeLSTM
](
http://arxiv.org/abs/1503.00075
)
| 51.0% | 51.72% |
[
14.02s (DyNet)
](
https://github.com/clab/dynet/tree/master/examples/treelstm
)
| 3.18s | 4.3x |
|
[
R-GCN <br> (classification)
](
https://arxiv.org/abs/1703.06103
)
| 73.23% | 73.53% |
[
0.2853s (Theano)
](
https://github.com/tkipf/relational-gcn
)
| 0.0
273
s |
10
.4x |
|
[
R-GCN <br> (classification)
](
https://arxiv.org/abs/1703.06103
)
| 73.23% | 73.53% |
[
0.2853s (Theano)
](
https://github.com/tkipf/relational-gcn
)
| 0.0
097
s |
29
.4x |
|
[
R-GCN <br> (link prediction)
](
https://arxiv.org/abs/1703.06103
)
| 0.158 | 0.151 |
[
2.204s (TF)
](
https://github.com/MichSchli/RelationPrediction
)
| 0.
63
3s |
3.5
x |
|
[
R-GCN <br> (link prediction)
](
https://arxiv.org/abs/1703.06103
)
| 0.158 | 0.151 |
[
2.204s (TF)
](
https://github.com/MichSchli/RelationPrediction
)
| 0.
45
3s |
4.86
x |
|
[
JTNN
](
https://arxiv.org/abs/1802.04364
)
| 96.44% | 96.44% |
[
1826s (Pytorch)
](
https://github.com/wengong-jin/icml18-jtnn
)
| 743s | 2.5x |
|
[
JTNN
](
https://arxiv.org/abs/1802.04364
)
| 96.44% | 96.44% |
[
1826s (Pytorch)
](
https://github.com/wengong-jin/icml18-jtnn
)
| 743s | 2.5x |
|
[
LGNN
](
https://arxiv.org/abs/1705.08415
)
| 94% | 94% | n/a | 1.45s | n/a |
|
[
LGNN
](
https://arxiv.org/abs/1705.08415
)
| 94% | 94% | n/a | 1.45s | n/a |
|
[
DGMG
](
https://arxiv.org/pdf/1803.03324.pdf
)
| 84% | 90% | n/a | 238s | n/a |
|
[
DGMG
](
https://arxiv.org/pdf/1803.03324.pdf
)
| 84% | 90% | n/a | 238s | n/a |
...
@@ -31,6 +31,11 @@ a model similar to GCN.
...
@@ -31,6 +31,11 @@ a model similar to GCN.
We are currently in Beta stage. More features and improvements are coming.
We are currently in Beta stage. More features and improvements are coming.
## News
v0.2 has just been released! Many features, bugfix and performance improvement. See release note
[
here
](
https://github.com/dmlc/dgl/releases/tag/v0.2
)
.
## System requirements
## System requirements
DGL should work on
DGL should work on
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment