mirrors / dmlc--dgl

文件历史

3,326 提交 34 分支 42 Git 标签
peizhou/negative__patch
提交图

655 次代码提交

作者 SHA1 备注 提交日期
Muhammed Fatih BALIN 7e4c226de4 [Model] Simplify labor example, add proper inference code (#6104) 2023-08-10 11:54:13 +08:00
Andrei Ivanov 8b35cbc80a Improving the DEEPWALK example. (#6070) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-08-07 10:16:04 +08:00
Andrei Ivanov e0aa838971 Improving the CLUSTER_GAT example. (#6059) 2023-08-04 11:16:25 +08:00
Andrei Ivanov d20db1ec92 Improving the RGCN_HETERO example (#6060) 2023-08-04 10:29:39 +08:00
Muhammed Fatih BALIN bdbc0178ef [Example] Labor sampling (#4718) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-08-03 16:20:01 +08:00
Andrei Ivanov 158b0fcdc7 Improving the citation_network example. (#6032) 2023-08-03 13:49:53 +08:00
Andrei Ivanov 61b2f4e281 Improving the APPNP example. (#6054) 2023-08-03 13:49:34 +08:00
Andrei Ivanov 31f1b30c3e Improving the GGNN example. (#6055) 2023-08-03 13:47:12 +08:00
Andrei Ivanov ec7137dddf Improving the PinSAGE example. (#6067) 2023-08-03 13:19:54 +08:00
Andrei Ivanov 562a1c878e Improving the CompGCN example. (#6068) 2023-08-03 13:15:00 +08:00
Andrei Ivanov 2584f3af10 Improving the HGT example. (#6069) 2023-08-03 12:53:41 +08:00
Andrei Ivanov ee6518113f Improving the output for the Cluster GCN example. (#6079) 2023-08-03 10:32:24 +08:00
Songqing Zhang 9711d75fda [Misc] Simplify the data path's assignment in python utils (#6058) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-08-02 12:43:13 +08:00
Andrei Ivanov 17f6c4c9c1 Improving the PAGERANK example. (#6066) 2023-08-01 16:18:24 +08:00
Ilia Taraban 8c213ef122 [Feature] Enable bfloat16 convert functions in Python API (#5760) 2023-07-31 18:09:32 +08:00
Andrei Ivanov 0c3b2b780f Improving the HARD_GAT example (#6036) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-07-27 14:05:01 +08:00
Andrei Ivanov 885b0eae92 Improving the DGI example. (#6034) 2023-07-27 13:55:36 +08:00
Andrei Ivanov 1f9310117d Improving the GATv2 example. (#6035) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-07-27 13:43:18 +08:00
Andrei Ivanov 017d9d4010 [Fix][Readability] Improving the Capsule Network example. (#5985) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-07-27 13:15:48 +08:00
Andrei Ivanov 87a41e502d Improving the MoNet example. (#5999) 
Co-authored-by: rudongyu <ru_dongyu@outlook.com>
 2023-07-27 13:02:21 +08:00
Andrei Ivanov c334662bdb Removing warnings in the EEG-GNN example. (#5925) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-07-27 08:58:44 +08:00
Andrei Ivanov a64ff4825a Removing the UserWarning appearing in the mnist example. (#6000) 
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
 2023-07-14 13:30:12 +08:00
Andrei Ivanov b35f15b7f1 [Doc]Removing useless dataset loading instructions for the P-GNN example. (#5861) 
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-06-13 13:20:38 +08:00
hummingg 5641594c36 AIFB -> AIFBDataset (#5860) 2023-06-13 01:55:33 +08:00
Rhett Ying c9778b5522 [DistDGL] remove use of tensorpipe from examples and docs (#5837) 2023-06-09 08:55:53 +08:00
Rhett Ying b6f774cd83 [Examples] fix lint (#5838) 2023-06-08 17:21:38 +08:00
Andrei Ivanov d1247b6f32 [Misc]Improving the output of the DCRNN training script. (#5790) 
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2023-06-07 12:00:28 +08:00
Chang Liu 23772ee160 [Example][Minor] Update README/requirements from sklearn -> scikit-learn (#5792) 2023-06-07 10:33:31 +08:00
Rhett Ying d64f7c4808 [Benchmark] log train time and test accuracy, choose device (#5662) 2023-05-10 14:59:21 +08:00
czkkkkkk f41934df87 [Sparse] Add conversion between DGLGraph and SparseMatrix. (#5553) 2023-04-20 18:00:34 +08:00
Mufei Li a1f7498240 [Example] Fix Various Examples Related to TorchMetrics (#5521) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-36-188.ap-northeast-1.compute.internal>
 2023-04-10 15:54:00 +08:00
Hongzhi (Steve), Chen 5008af2210 [Misc] Rename number_of_edges and number_of_nodes to num_edges and num_nodes in examples. (#5492) 
* pytorch_example

* fix

---------

Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>
 2023-03-29 11:01:20 +08:00
Mufei Li a07305301e Update main.py (#5460) 2023-03-22 21:01:16 +08:00
Minjie Wang 8d99d30a82 add a link about the removed TGN example (#5456) 2023-03-15 22:08:38 +08:00
Hongzhi (Steve), Chen 9fe5092c17 lintrunner (#5326) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>
 2023-02-19 22:50:07 +08:00
Hongzhi (Steve), Chen 704bcaf6dd examples (#5323) 
Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>
 2023-02-19 08:35:15 +08:00
Hongzhi (Steve), Chen b3308ae795 Cleanup mock_sparse related code. (#5230) 
* remove_mock_sparse_example

* mock_sparse_test

* remove_mock_sparse

---------

Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
 2023-02-01 15:17:14 +08:00
Xin Yao cdfd1e382f Delete train_sampling_unsupervised.py (#5161) 2023-01-12 11:15:48 -08:00
peizhou001 436de3d120 [API Deprecation] Remove _dataloading and tgcn example (#5118) 2023-01-06 19:51:55 +08:00
peizhou001 c55ab2d147 deprecate candidates in dataloader (#5117) 2023-01-06 16:18:32 +08:00
Chang Liu a506ebe82b [Example][Refactor] Multi-gpu graphsage link prediction example refactor (#5091) 2023-01-05 20:59:39 +08:00
Dylan b84de903a2 GCN example correction (#4969) (#4976) 
Correction like mentioned in #4969 

I noticed that there is a normalisation step on line 97 while the normalised values are not used downstream. Even if this was meant to show the normalisation step, it would not be calculating the normalisation step described in the CGN paper. The paper considers both in and out degrees while the normalisation in the code only describes normalisation using the in degrees.
In the end, the normalised values are assigned to g.ndata["norm"] but these values are not used afterwards.

Having a normalisation step here is also unnecessary since the GraphConv layer that is used already takes care of the normalisation. https://docs.dgl.ai/en/0.9.x/_modules/dgl/nn/pytorch/conv/graphconv.html#GraphConv

It confused me for a second thinking that I had to do the normalisation myself but this is already handled by the GraphConf.
 2022-12-05 10:00:57 +08:00
peizhou001 611393021a [API Deprecation] Remove candidates in DGLGraph (#4946) 2022-12-01 16:41:53 +08:00
Hongzhi (Steve), Chen 226d1159a9 [Misc] Auto fix by black. (#4952) 
* black on explain_main

* isort

* add dot

Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
 2022-11-25 09:24:44 +08:00
Hongzhi (Steve), Chen f118ea9537 black (#4951) 
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
 2022-11-25 09:19:17 +08:00
Rhett Ying b377e1b9c1 [Dist][Examples] refactor dist graphsage examples (#4269) 
* [Dist][Examples] refactor dist graphsage examples

* refine train_dist.py

* update train_dist_unsupervised.py

* fix debug info

* update train_dist_transductive

* update unsupervised_transductive

* remove distgnn

* fix join() in standalone mode

* change batch_labels to long() for ogbn-papers100M

* free unnecessary mem

* lint

* fix lint

* refine

* fix lint

* fix incorrect args

* refine
 2022-11-17 08:35:15 +08:00
peizhou001 3132da2826 Deprecate (#4864) 
rename DGLHeteroGraph to DGLGraph
 2022-11-15 10:01:01 +08:00
Chang Liu 6566c31fba Fix ogb/ogbn-mag/heter-RGCN example (#4839) 
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2022-11-09 14:08:01 +08:00
Ereboas 7c788f531c [Example] Update SEAL+NGNN for ogbl-citation2 (#4776) 
* Use black for formatting

* limit line width to 80 characters.

* Use a backslash instead of directly concatenating

* file structure adjustment.

* file structure adjustment(2)

* codes for citation2

* format slight adjustment

* adjust format in models.py

* now it runs normally for all datasets.

* add comments; adjust code order.

* adjust indenting.

Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2022-11-03 10:24:03 +08:00
Ereboas f9805ef11c [Example] SEAL+NGNN for ogbl-citation2 (#4772) 
* Use black for formatting

* limit line width to 80 characters.

* Use a backslash instead of directly concatenating

* file structure adjustment.

* file structure adjustment(2)

* codes for citation2

* format slight adjustment

* adjust format in models.py

* now it runs normally for all datasets.

Co-authored-by: Mufei Li <mufeili1996@gmail.com>
 2022-10-28 00:31:24 +08:00