3317522 | Hengrui Zhang | 09 March 2021, 07:26:11 UTC | [Example] Add implementation of InfoGraph (#2644) * Add implementation of unsupervised model * [Doc] Update Implementor's information * [doc] add index of infograph * [Feature] QM9_v2 Dataset Support * fix a typo * move qm9dataset from data to examples * Update qm9_v2.py * Infograph -> InfoGraph * add implementation and results of semi-supervised model * Update README.md * Update README.md * fix a typo * Remove the duplicated links. * fix some typos * fix typos * update model.py * update collate fn * remove unused functions * Update model.py * add device option * Update evaluate_embedding.py * Update evaluate_embedding.py * Update unsupervised.py * Fix typos * fix bugs * Update README.md Co-authored-by: Mufei Li <mufeili1996@gmail.com> | 09 March 2021, 07:26:11 UTC |
a1f59c3 | Hengrui Zhang | 09 March 2021, 06:51:21 UTC | [Feature] QM9Edge Dataset Support (#2704) * [Feature] Support QM9Edge Datset * Update qm9_edge.py * disable tqdm * Update qm9_edge.py * Update qm9_edge.py * Update qm9_edge.py * Update qm9_edge.py * Update qm9_edge.py * Update qm9_edge.py * Update qm9_edge.py * remove preprocessing part * add comparisons in qm9.py * [docs] add qm9edge dataset Co-authored-by: Mufei Li <mufeili1996@gmail.com> | 09 March 2021, 06:51:21 UTC |
62dd1c8 | maqy1995 | 05 March 2021, 15:30:21 UTC | fix doc typo (#2721) | 05 March 2021, 15:30:21 UTC |
7380d61 | Mufei Li | 03 March 2021, 08:35:07 UTC | [NN] Support Unidirectional Bipartite Graphs in CFConv (#2674) * Update * update * Update Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 03 March 2021, 08:35:07 UTC |
97bdae9 | Quan (Andy) Gan | 02 March 2021, 14:16:31 UTC | [Docker] Add Dependency Packages for CI (#2713) * add ogb to docker build * mxnet 1.6 disappeared | 02 March 2021, 14:16:31 UTC |
f793864 | Yu Sun | 02 March 2021, 02:24:34 UTC | [Example] Variational Graph Auto-Encoders (#2587) * [Example]Variational Graph Auto-Encoders * change dgl dataset to single directional graph * clean code * refresh Co-authored-by: Tianjun Xiao <xiaotj1990327@gmail.com> | 02 March 2021, 02:24:34 UTC |
d0638b1 | Da Zheng | 01 March 2021, 20:00:15 UTC | [Example] Update the example of distributed GNN training of RGCN (#2709) * support gpu training. * remove unnecessary arguments. * update README. * update time measurement. * add zero_grad. Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-132.us-west-1.compute.internal> Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 01 March 2021, 20:00:15 UTC |
668bd92 | Minjie Wang | 01 March 2021, 11:25:19 UTC | [Doc] Add TDC to paper list | 01 March 2021, 11:25:19 UTC |
062f59a | Padarn Wilson | 28 February 2021, 09:37:13 UTC | fix small typo bug (#2708) Co-authored-by: Zihao Ye <expye@outlook.com> | 28 February 2021, 09:37:13 UTC |
28b0a76 | Da Zheng | 28 February 2021, 02:34:46 UTC | [Example] Provide instructions of setting up passwordless SSH login. (#2707) | 28 February 2021, 02:34:46 UTC |
5087a21 | Quan (Andy) Gan | 26 February 2021, 07:09:18 UTC | Update README.md (#2705) | 26 February 2021, 07:09:18 UTC |
6568d0a | Ligeng Zhu | 25 February 2021, 12:20:52 UTC | [Example] Recommend NFS over copy files (#2689) * Update README to use NFS, rather than copying files * Update README.md * Update README.md * Update README.md * Add ParMetis * Update README.md * fix directory. * fix * redo. * fix. * update. * add more descriptions Co-authored-by: Da Zheng <zhengda1936@gmail.com> Co-authored-by: Quan Gan <coin2028@hotmail.com> | 25 February 2021, 12:20:52 UTC |
99751d4 | Quan (Andy) Gan | 25 February 2021, 10:26:19 UTC | [Doc] Rename block to message flow graph (#2702) * rename block to mfg * revert * rename | 25 February 2021, 10:26:19 UTC |
491d908 | xnouhz | 25 February 2021, 09:38:43 UTC | [Example] Add ARMA for Node Classification (#2694) * [example] arma * update * update * update * update * update Co-authored-by: Mufei Li <mufeili1996@gmail.com> | 25 February 2021, 09:38:43 UTC |
583aa76 | Smile | 25 February 2021, 07:53:35 UTC | [Example] Pytorch Seal example (#2638) * add seal example * 1. add paper infomation in examples/README 2. adjust codes 3. option test * use latest `to_simple` to replace coalesce graph function * remove outdated codes * remove useless comment | 25 February 2021, 07:53:35 UTC |
0526b88 | Da Zheng | 25 February 2021, 04:41:41 UTC | [Distributed] Fix the path for distributed partitioning. (#2700) Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-132.us-west-1.compute.internal> | 25 February 2021, 04:41:41 UTC |
7ab3d99 | Ligeng Zhu | 25 February 2021, 00:12:19 UTC | Change the absolute path to relative one in `part_config.json` (#2690) * Update partition.py * fix lint. Co-authored-by: Da Zheng <zhengda1936@gmail.com> | 25 February 2021, 00:12:19 UTC |
1686106 | Quan (Andy) Gan | 24 February 2021, 16:21:00 UTC | change __repr__ (#2696) Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 24 February 2021, 16:21:00 UTC |
704ec68 | Jinjing Zhou | 24 February 2021, 11:41:49 UTC | [Benchmark] Fix benchmark tests and add script to generate excel result (#2681) * add script * 21 * log * fix regression tests * add iter time * fix * Revert "fix" This reverts commit 9b4587ad61dfeb82dcce6d1de188809f62947663. * fix * fix * add * add ogb instruction * add cu11 dockerfile * fix * fix * more iter apply_edge * add iteration time Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 24 February 2021, 11:41:49 UTC |
71d53d9 | Quan (Andy) Gan | 23 February 2021, 12:33:35 UTC | add thumbnails for tutorials (#2695) Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 23 February 2021, 12:33:35 UTC |
da2f690 | Quan (Andy) Gan | 23 February 2021, 11:41:54 UTC | [Doc] Clarify link prediction tutorial (#2673) * link prediction clarification * fix | 23 February 2021, 11:41:54 UTC |
7298173 | Tong He | 23 February 2021, 07:14:10 UTC | [Doc]Improve docstring for GINDataset (#2676) * add docstring for gin * update doc Co-authored-by: Mufei Li <mufeili1996@gmail.com> | 23 February 2021, 07:14:10 UTC |
174dd18 | Zihao Ye | 23 February 2021, 06:19:51 UTC | [hotfix] A bunch of fix for SetTransformer (#2658) * upd * lint * upd * fix * fix * upd * upd * fix * warning * upd * upd | 23 February 2021, 06:19:51 UTC |
48a1794 | Da Zheng | 23 February 2021, 02:59:15 UTC | [Doc] Fix the user guide for distributed partitioning. (#2684) * fix doc. * explain the schema file. * fix. | 23 February 2021, 02:59:15 UTC |
80c2687 | xiang song(charlie.song) | 22 February 2021, 03:33:44 UTC | [Bug Fix] Fix munmap bug in sparse optimizer (#2675) * Fix munmap bug * lint * update Co-authored-by: Ubuntu <ubuntu@ip-172-31-56-220.ec2.internal> | 22 February 2021, 03:33:44 UTC |
16e324d | xiang song(charlie.song) | 22 February 2021, 02:12:40 UTC | [Bug Fix] Add warning for invalid input graph of edge UDF (#2682) * Add warning for invalid graph of edge UDF * lint Co-authored-by: Ubuntu <ubuntu@ip-172-31-56-220.ec2.internal> | 22 February 2021, 02:12:40 UTC |
72a16b2 | Zihao Ye | 21 February 2021, 10:52:35 UTC | [bugfix] Fix the behavior of select_topk (#2688) * fix * lint * lint | 21 February 2021, 10:52:35 UTC |
e6bf54c | Zihao Ye | 21 February 2021, 02:05:42 UTC | [Feature] Support aggregate multiple edge features in to_simple. (#2623) * upd * fix * upd * upd * upd * upd * upd * upd * upd * upd * upd * fix * refactor * upd test * large feat_len or n in segment reduce * lint | 21 February 2021, 02:05:42 UTC |
8a07ab7 | Minjie Wang | 20 February 2021, 09:42:45 UTC | [Doc] Tutorials re-organization (#2683) * reorg * change titles * rm some stale API doc; minor fix * fix docs * add warning * rm new-tutorial run in ci * lint | 20 February 2021, 09:42:45 UTC |
0fc6495 | Da Zheng | 19 February 2021, 18:48:05 UTC | [Doc] Distributed heterogeneous graph training (#2654) * update DistGraph docstrings. * add user guide. * add doc string. * fix. * fix. * fix. Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 19 February 2021, 18:48:05 UTC |
453d358 | xiang song(charlie.song) | 19 February 2021, 06:07:35 UTC | [Doc] Fix docs for sparse optimizer (#2680) Co-authored-by: Ubuntu <ubuntu@ip-172-31-56-220.ec2.internal> Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 19 February 2021, 06:07:35 UTC |
9e04a52 | Quan (Andy) Gan | 19 February 2021, 05:49:13 UTC | [Doc] Reorganize tutorial (#2678) | 19 February 2021, 05:49:13 UTC |
dda103d | Quan (Andy) Gan | 19 February 2021, 05:07:21 UTC | Fix bug in EdgeConv implementation (#2669) * Update edgeconv.py * update edgeconv to builtin * add explanation on why ReLU is not there * remove redundant code | 19 February 2021, 05:07:21 UTC |
d93a975 | Quan (Andy) Gan | 19 February 2021, 04:05:42 UTC | revert (#2672) | 19 February 2021, 04:05:42 UTC |
ff64bd0 | Da Zheng | 16 February 2021, 08:16:40 UTC | add warning for a bug in README (#2665) | 16 February 2021, 08:16:40 UTC |
0cbaa1f | Zihao Ye | 12 February 2021, 04:29:22 UTC | [Doc] Make the docstring of nn.glob more informative. (#2649) * upd * fix weight and sum * upd sortpool | 12 February 2021, 04:29:22 UTC |
9e63010 | Quan (Andy) Gan | 12 February 2021, 03:40:05 UTC | fix and lots of tests (#2650) | 12 February 2021, 03:40:05 UTC |
cf8a3fb | Zihao Ye | 10 February 2021, 16:00:39 UTC | [hotfix] Address the performance issue of topk. (#2628) * upd * fix * upd * upd * udp * upd * upd * upd * upd * upd * upd Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 10 February 2021, 16:00:39 UTC |
e46983f | Tianqi Zhang (张天启) | 10 February 2021, 03:21:34 UTC | [Bug Fix][Example] fix dataloader bug in gxn (#2631) Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 10 February 2021, 03:21:34 UTC |
22ccf43 | Minjie Wang | 09 February 2021, 03:08:55 UTC | [Test] Tweak end2end benchmarks to be more reasonable (#2643) * change timeout to reasonable ranges * rgcn ns * fix all ns speed tests Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 09 February 2021, 03:08:55 UTC |
e4ff484 | Da Zheng | 09 February 2021, 01:19:18 UTC | [Distributed] Distributed METIS partition (#2576) * add convert. * fix. * add write_mag. * fix convert_partition.py * write data. * use pyarrow to read. * update write_mag.py * fix convert_partition.py. * load node/edge features when necessary. * reshuffle nodes. * write mag correctly. * fix a bug: inner nodes in a partition might be empty. * fix bugs. * add verify code. * insert reverse edges. * fix a bug. * add get node/edge data. * add instructions. * remove unnecessary argument. * update distributed preprocessing. * fix readme. * fix. * fix. * fix. * fix readme. * fix doc. * fix. * update readme * update doc. * update readme. Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-132.us-west-1.compute.internal> Co-authored-by: Ubuntu <ubuntu@ip-172-31-2-202.us-west-1.compute.internal> | 09 February 2021, 01:19:18 UTC |
0aca566 | Jinjing Zhou | 08 February 2021, 09:01:35 UTC | [Regression] Fix regression tests (#2639) * add bench jenkins * instance type * fix * fix * fix * 111 * test * 111 * 111 * fix * test * run * fix * fix * fix * fix * fix * publish results * 111 * regression * launch ec2 script * fix * add * run on master * change * rrr * run gpu * fix * fix * try fix * fix * ff * fix * fix * fix * refactor * fix * fix * update * fix * fix * fix * fix * remove import torchtext * add shm size * update * fix * fix * fix * fix * fix this!!!! * 111 * fix * remove verbose * fix * fix * fix * fix * fix * fix * fix * fix * update readme * fix * fix * fix * change asv default to head * commit sage and rgcn * fix * update * add benchmarks * add * fix * update * remove RandomState * tmp remove * new batch * fix * fix * fix * address comment * fix warning * fix * fix * fix * fix * add multiupdate all * address comment * fix * add benchmarks * add * fix timing * fix * push * add -v * [Example] NGCF (#2564) * ngcf * ngcf * update Co-authored-by: zhjwy9343 <6593865@qq.com> * Revert "[Example] NGCF (#2564)" (#2611) This reverts commit a75e04f408c719289f478ca129784e05655d8def. * fix * change task * fix * fix * fix2 * enable tensoradapter when benchmark * minor fix * trigger ci * fix * fix * fix * fix * fix * fix * lint * fix Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> Co-authored-by: KounianhuaDu <51199171+KounianhuaDu@users.noreply.github.com> Co-authored-by: zhjwy9343 <6593865@qq.com> | 08 February 2021, 09:01:35 UTC |
117dd25 | Quan (Andy) Gan | 08 February 2021, 08:33:39 UTC | [Doc] Fix inconsistencies and GPU code (#2642) * fix inconsistencies and GPu * bug fixes * fix * trigger new tutorials | 08 February 2021, 08:33:39 UTC |
8ccb820 | Tong He | 08 February 2021, 06:43:24 UTC | [Doc] Update docs to motivate the use of set_batch_num_nodes and set_batch_num_edges (#2630) * fix doc * update docstring for transformation on batch graph * update cn guide * fix format * update rst | 08 February 2021, 06:43:24 UTC |
48d357b | xiang song(charlie.song) | 08 February 2021, 06:05:30 UTC | Fix numbers (#2641) Co-authored-by: Ubuntu <ubuntu@ip-172-31-56-220.ec2.internal> | 08 February 2021, 06:05:30 UTC |
bc3a532 | nv-dlasalle | 08 February 2021, 05:00:43 UTC | [Sampling] Implement `dgl.to_block()` for the GPU (#2339) * Add start of to_block gpu implementation * Pull in more changes from 0.4.2 cuda_to_block * Move more code to IdArray * Refactor DeviceNodeMapMaker * Updates * get compiling * Integrate to_block * Fix ID allocation * Minor fixes * Cleanup cuda calls to use cuda_common * Reduce kernel calls * Lint cleanup * Expand documentation * Remove unused function * Rename variables for consistency * Add doxygen comments * Fix file extension * Remove raw asynccopy for deviceapi * Remove unused function * Fix block/tile configuration * Add cuda_device_common.cuh * Add basic hashtable * Migrate part of hashtable * Refactor to use external hashtable * Make functions members * Format hash table functions * Migrate duplicate filling * Move last function over * Refactor with cu file * lint c++ code * Move context check to C++ code * Use macro switch * Add missing files * Update docstring * update docs * Move atomic functions * Refactor hashtable * Fix linting * Expand docs * Fix mismatched argument names * Switch doxygen comments from using @param to \param Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 08 February 2021, 05:00:43 UTC |
ae18d7f | Tianjun Xiao | 08 February 2021, 02:42:32 UTC | [Example]Add dependencies for GNN-Film and dagnn (#2633) * add dependencies for GNN-Film and dagnn * fix * fix * fix | 08 February 2021, 02:42:32 UTC |
98ac391 | Quan (Andy) Gan | 07 February 2021, 09:55:49 UTC | [Doc] Large graph training tutorials (#2595) * large graph training tutorials * add full graph link prediction update * fix * fix * fix * addressed comments | 07 February 2021, 09:55:49 UTC |
0346b0a | Jinjing Zhou | 05 February 2021, 14:38:46 UTC | [Test] Add test for Cython and force rebuild when run setup.py (#2635) | 05 February 2021, 14:38:46 UTC |
3cf42fd | Tianqi Zhang (张天启) | 05 February 2021, 10:26:33 UTC | [Bug Fix][Example] hgp-sl: More info for running (#2634) * [Bug Fix][Example] hgp-sl: More info for running * change list to table * change dataset summary in gxn and sagpool * remove redundent Co-authored-by: Tong He <hetong007@gmail.com> | 05 February 2021, 10:26:33 UTC |
3ca52b1 | Mufei Li | 05 February 2021, 09:34:16 UTC | [Fix] Various Fix after Bug Bash (#2620) * update * Misc fix * Update | 05 February 2021, 09:34:16 UTC |
f8c9d58 | Chen Sirui | 05 February 2021, 08:52:41 UTC | [Bug] Hardgat enable gpu training (#2632) * add multihead in DotGatConv * Fix spacing issue * Add Unit test for dotgat * Modified Unit test for dotgat * Add transformer like divisor * Update dotgatconv.py * Update hgao.py * Update train.py Co-authored-by: Chen <chesirui@3c22fbe5458c.ant.amazon.com> Co-authored-by: Zihao Ye <expye@outlook.com> | 05 February 2021, 08:52:41 UTC |
23afe91 | xiang song(charlie.song) | 05 February 2021, 03:49:41 UTC | [Bug Fix] Fix several sparse optimizer bugs (#2596) * Fix pytorch TCP kvstore bug * lint * Fix * upd * Fix lint * Fix * trigger * fix Co-authored-by: Ubuntu <ubuntu@ip-172-31-56-220.ec2.internal> | 05 February 2021, 03:49:41 UTC |
2f71bc5 | KounianhuaDu | 04 February 2021, 16:32:21 UTC | [Example] Neural Graph Collaborative Filtering (NGCF). (#2612) * ngcf * ngcf * update * ngcf * ngcf * remove data * update * data Co-authored-by: zhjwy9343 <6593865@qq.com> Co-authored-by: Zihao Ye <expye@outlook.com> | 04 February 2021, 16:32:21 UTC |
469088e | Minjie Wang | 04 February 2021, 06:40:00 UTC | [Test] Add benchmarks for end-to-end training w/ UDF message passing (#2609) * model acc test * add model speed test * [Example] NGCF (#2564) * ngcf * ngcf * update Co-authored-by: zhjwy9343 <6593865@qq.com> * Revert "[Example] NGCF (#2564)" (#2611) This reverts commit d88a9b1b2c52becb8cc7faebceca6e52c763de19. * use timer Co-authored-by: KounianhuaDu <51199171+KounianhuaDu@users.noreply.github.com> Co-authored-by: zhjwy9343 <6593865@qq.com> Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> Co-authored-by: Zihao Ye <expye@outlook.com> | 04 February 2021, 06:40:00 UTC |
94ab970 | 张恒瑞 | 04 February 2021, 03:59:41 UTC | [Bugfix] fix a typo in consis_loss function (#2616) | 04 February 2021, 03:59:41 UTC |
ff345c2 | wcyjames | 03 February 2021, 14:15:46 UTC | [Example] update PointNet and PointNet++ examples for Part Segmentation (#2547) * [Model] update PointNet example for Part Segmentation * Fixed issues with pointnet examples * update the README * Added image * Fixed README and tensorboard arguments * clean * Add timing * Update README.md * Update README.md Fixed a typo Co-authored-by: Tong He <hetong007@gmail.com> | 03 February 2021, 14:15:46 UTC |
b1840f4 | Mufei Li | 03 February 2021, 13:00:45 UTC | [Dataset] Change the Data Type of the Node Features in GINDataset/TUDataset from Float64 to Float32 (#2592) * Update * Update * Update * update Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> Co-authored-by: Tong He <hetong007@gmail.com> | 03 February 2021, 13:00:45 UTC |
d460efe | Jinjing Zhou | 03 February 2021, 11:10:07 UTC | [Test] More regression tests (#2591) * add bench jenkins * instance type * fix * fix * fix * 111 * test * 111 * 111 * fix * test * run * fix * fix * fix * fix * fix * publish results * 111 * regression * launch ec2 script * fix * add * run on master * change * rrr * run gpu * fix * fix * try fix * fix * ff * fix * fix * fix * refactor * fix * fix * update * fix * fix * fix * fix * remove import torchtext * add shm size * update * fix * fix * fix * fix * fix this!!!! * 111 * fix * remove verbose * fix * fix * fix * fix * fix * fix * fix * fix * update readme * fix * fix * fix * change asv default to head * commit sage and rgcn * fix * update * add benchmarks * add * fix * update * remove RandomState * tmp remove * new batch * fix * fix * fix * address comment * fix warning * fix * fix * fix * fix * add multiupdate all * address comment * fix * add benchmarks * add * fix timing * fix * push * add -v * [Example] NGCF (#2564) * ngcf * ngcf * update Co-authored-by: zhjwy9343 <6593865@qq.com> * Revert "[Example] NGCF (#2564)" (#2611) This reverts commit a75e04f408c719289f478ca129784e05655d8def. * fix * change task * fix * fix * fix2 * enable tensoradapter when benchmark * minor fix * trigger ci * fix * fix Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> Co-authored-by: KounianhuaDu <51199171+KounianhuaDu@users.noreply.github.com> Co-authored-by: zhjwy9343 <6593865@qq.com> | 03 February 2021, 11:10:07 UTC |
fb4a050 | Zihao Ye | 03 February 2021, 10:50:07 UTC | [bugfix] Solve the boundary issue in backward function of segment sum (#2610) * upd * trigger * upd | 03 February 2021, 10:50:07 UTC |
b04cf65 | S22 | 03 February 2021, 09:27:20 UTC | [Bugfix] Fix sparseadam bug in metapath2vec(pytorch) (#2607) It seems that there is a bug in Sparseadam in PyTorch, and it can be temporarily fixed by: optimizer = optim.SparseAdam(list(self.skip_gram_model.parameters()), lr=self.initial_lr) Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 03 February 2021, 09:27:20 UTC |
47c9380 | Quan (Andy) Gan | 02 February 2021, 08:23:54 UTC | [Performance] Fix Cython not being imported after switching to RTLD_LOCAL (#2608) * fix * ? Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 02 February 2021, 08:23:54 UTC |
20d4977 | Yu Sun | 02 February 2021, 07:52:43 UTC | [Feature] Add reverse edges in CitationGraphDataset (#2588) * [Feature] Add reverse edges in CitationGraphDataset * fix bug * fix bug * fix bug * Update python/dgl/data/citation_graph.py Co-authored-by: Xiangkun Hu <huxk_hit@qq.com> * fix notes * fix notes * fix bugs * solve requested changes * fix bug * fix bug Co-authored-by: Xiangkun Hu <huxk_hit@qq.com> | 02 February 2021, 07:52:43 UTC |
3a19bbc | Quan (Andy) Gan | 02 February 2021, 03:04:43 UTC | fix doc (#2604) | 02 February 2021, 03:04:43 UTC |
db57809 | Zihao Ye | 31 January 2021, 05:08:05 UTC | [hotfix] Add data type check for kernels. (#2598) * upd * upd | 31 January 2021, 05:08:05 UTC |
460bb42 | Quan (Andy) Gan | 29 January 2021, 09:46:31 UTC | fix build problems (#2594) | 29 January 2021, 09:46:31 UTC |
1f6eba9 | Quan (Andy) Gan | 29 January 2021, 01:30:19 UTC | [Bug] Heterogeneous graph convolution bugfix (#2578) * fix heterograph conv * remove test cases * fix test * fix test * fix test Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 29 January 2021, 01:30:19 UTC |
e4ddafe | Chen Sirui | 28 January 2021, 13:05:10 UTC | [NN] add multihead in DotGatConv (#2549) * add multihead in DotGatConv * Fix spacing issue * Add Unit test for dotgat * Modified Unit test for dotgat * Add transformer like divisor * Update dotgatconv.py Co-authored-by: Chen <chesirui@3c22fbe5458c.ant.amazon.com> Co-authored-by: Zihao Ye <expye@outlook.com> | 28 January 2021, 13:05:10 UTC |
4ca706e | Minjie Wang | 28 January 2021, 08:32:18 UTC | [Doc] Update doc of dgl.function (#2585) * update doc of dgl.function * small fix | 28 January 2021, 08:32:18 UTC |
6ce2dc3 | Jinjing Zhou | 28 January 2021, 07:50:05 UTC | [Test] Regression Test for update_all and apply_edges (#2568) * add bench jenkins * instance type * fix * fix * fix * 111 * test * 111 * 111 * fix * test * run * fix * fix * fix * fix * fix * publish results * 111 * regression * launch ec2 script * fix * add * run on master * change * rrr * run gpu * fix * fix * try fix * fix * ff * fix * fix * fix * refactor * fix * fix * update * fix * fix * fix * fix * remove import torchtext * add shm size * update * fix * fix * fix * fix * fix this!!!! * 111 * fix * remove verbose * fix * fix * fix * fix * fix * fix * fix * fix * update readme * fix * fix * fix * change asv default to head * commit sage and rgcn * fix * update * add benchmarks * add * fix * update * remove RandomState * tmp remove * new batch * fix * fix * fix * address comment * fix warning * fix * fix * fix * fix * add multiupdate all * address comment * fix Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 28 January 2021, 07:50:05 UTC |
fb3c070 | Zihao Ye | 28 January 2021, 06:53:55 UTC | Revert part of #2563 (#2584) | 28 January 2021, 06:53:55 UTC |
878acdb | Minjie Wang | 28 January 2021, 06:04:07 UTC | Revert "Refactor code for retaining formats in message-passing. (#2570)" (#2583) This reverts commit a613ad880690a8b155537117ea038a9de14111ed. | 28 January 2021, 06:04:07 UTC |
7bab136 | Zihao Ye | 28 January 2021, 03:21:58 UTC | [feature] Supporting half precision floating data type (fp16). (#2552) * add tvm as submodule * compilation is ok but calling fails * can call now * pack multiple modules, change names * upd * upd * upd * fix cmake * upd * upd * upd * upd * fix * relative path * upd * upd * upd * singleton * upd * trigger * fix * upd * count reducible * upd * upd * upd * upd * upd * upd * upd * upd * upd * only keep related files * upd * upd * upd * upd * lint * lint * lint * lint * pylint * upd * upd * compilation * fix * upd * upd * upd * upd * upd * upd * upd doc * refactor * fix * upd number Co-authored-by: Zhi Lin <linzhilynn@gmail.com> Co-authored-by: Ubuntu <ubuntu@ip-172-31-42-78.us-east-2.compute.internal> Co-authored-by: Ubuntu <ubuntu@ip-172-31-21-156.us-east-2.compute.internal> Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 28 January 2021, 03:21:58 UTC |
a7e941c | xiang song(charlie.song) | 27 January 2021, 16:26:49 UTC | [Feature] Add support for sparse embedding (#2451) * Add sparse embedding for dgl and update rgcn example * upd * Fix * Revert "Fix" This reverts commit 4da87cdfb8b8c3506b7fc7376cd2385ba8045c2a. * Fix * upd * upd * Fix * Add unitest and update impl * fix * Clean up rgcn example code * upd * upd * update * Fix * update score * sparse for sage * remove model sparse * upd * upd * remove global norm * revert delete model_sparse.py * update according to comments * Fix doc * upd * Fix test * upd * lint * lint * lint * upd * upd * clean up Co-authored-by: Ubuntu <ubuntu@ip-172-31-56-220.ec2.internal> | 27 January 2021, 16:26:49 UTC |
362f72c | Minjie Wang | 27 January 2021, 13:29:48 UTC | [Test] Performance benchmarks for DGL kernels (#2582) * add initial kernel benchmarks * finished kernel benchmarks * add desc | 27 January 2021, 13:29:48 UTC |
12f6429 | Tong He | 27 January 2021, 10:49:40 UTC | remove hash_func from dataset object (#2572) Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 27 January 2021, 10:49:40 UTC |
8e981db | Tianqi Zhang (张天启) | 27 January 2021, 10:14:27 UTC | [Example] Add Graph Cross Net (GXN) example for pytorch backend (#2559) * add sagpool example for pytorch backend * polish sagpool example for pytorch backend * [Example] SAGPool: use std variance * [Example] SAGPool: change to std * add sagpool example to index page * add graph property prediction tag to sagpool * [Example] add graph classification example HGP-SL * [Example] fix sagpool * fix bug * [Example] change tab to space in README of hgp-sl * remove redundant files * remote redundant network * [Example]: change link from code to doc in HGP-SL * [Example] in HGP-SL, change to meaningful name * [Example] Fix path mistake for 'hardgat' * [Bug Fix] Fix undefined var bug in LegacyTUDataset * upt * [Bug Fix] Fix cache file name bug in TUDataset * [Example] Add GXN example for pytorch backend * modify readme * add more exp result Co-authored-by: zhangtianqi <tianqizh@amazon.com> Co-authored-by: Tong He <hetong007@gmail.com> | 27 January 2021, 10:14:27 UTC |
9fc5eed | Minjie Wang | 27 January 2021, 09:24:28 UTC | [Doc] Fix docstring of aten::Sort (#2579) A small patch to #2391. | 27 January 2021, 09:24:28 UTC |
2576647 | nv-dlasalle | 27 January 2021, 07:33:34 UTC | [Performance] Improve COO to CSR, and sort columns of CSR only when necessary. (#2391) * Remove double-checking sorted * Remove sorting of CSR by default * Update unit test to use unsorted matix * delete whitespace * Expand unit tests * Replace cusparse sort * Fix row column sorting * Explicitly don't sort columns * Fix linting errors * Fix bit-width calculation * Fix sorting assertion and unit test * Fix linting * Improve CPU COO2CSR * Remove references * Rename and add documentation to edge encoding/decoding funcionts * Fix sorting keys as 64 bit * Revert cosmetic changes to unit tests * Update documentation * Update complexity documentation for coo to csr conversion * Remove COOIsSorted check in CPU implementation too | 27 January 2021, 07:33:34 UTC |
0855d25 | Tong He | 26 January 2021, 15:34:12 UTC | [NN] Support scalar edge weight for GraphConv, SAGEConv and GINConv (#2557) * add edge weight in forward * fix lint * fix * fix * address comments * add utils * add util to normalize in gcn way * fix lint * add unittest * fix lint * fix docstring * fix docstring * address comments * improve notation consistence * use preferred fn | 26 January 2021, 15:34:12 UTC |
8900450 | lt610 | 26 January 2021, 09:06:32 UTC | [Example] DAGNN (#2545) * dagnn * dagnn * Update README.md * Update README.md * fixed some details * fixed some details * Update README.md * Update README.md Co-authored-by: Mufei Li <mufeili1996@gmail.com> | 26 January 2021, 09:06:32 UTC |
c45f6eb | Jinjing Zhou | 26 January 2021, 07:30:27 UTC | [Bugfix] Fix duplicate edges in Coauthor Dataset #2553 (#2569) * fix * address comment | 26 January 2021, 07:30:27 UTC |
6c23fba | Quan (Andy) Gan | 26 January 2021, 04:46:37 UTC | [Doc][Org] move edge_softmax to functional (#2442) * move edge_softmax to functional * change examples * fixes * revert * fix * fix * remove * fix * test * add init Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 26 January 2021, 04:46:37 UTC |
a613ad8 | Zihao Ye | 25 January 2021, 08:55:16 UTC | Refactor code for retaining formats in message-passing. (#2570) | 25 January 2021, 08:55:16 UTC |
0f9056e | Zihao Ye | 25 January 2021, 08:15:22 UTC | [feature] Implement missing CUDA operators for COO format (part 1). (#2565) * upd * upd * upd * upd * fix * upd * upd Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 25 January 2021, 08:15:22 UTC |
25ac334 | Da Zheng | 25 January 2021, 03:18:00 UTC | [Distributed] Heterogeneous graph support (#2457) * Distributed heterograph (#3) * heterogeneous graph partition. * fix graph partition book for heterograph. * load heterograph partitions. * update DistGraphServer to support heterograph. * make DistGraph runnable for heterograph. * partition a graph and store parts with homogeneous graph structure. * update DistGraph server&client to use homogeneous graph. * shuffle node Ids based on node types. * load mag in heterograph. * fix per-node-type mapping. * balance node types. * fix for homogeneous graph * store etype for now. * fix data name. * fix a bug in example. * add profiler in rgcn. * heterogeneous RGCN. * map homogeneous node ids to hetero node ids. * fix graph partition book. * fix DistGraph. * shuffle eids. * verify eids and their mappings when loading a partition. * Id map from homogneous Ids to per-type Ids. * verify partitioned results. * add test for distributed sampler. * add mapping from per-type Ids to homogeneous Ids. * update example. * fix DistGraph. * Revert "add profiler in rgcn." This reverts commit 36daaed8b660933dac8f61a39faec3da2467d676. * add tests for homogeneous graphs. * fix a bug. * fix test. * fix for one partition. * fix for standalone training and evaluation. * small fix. * fix two bugs. * initialize projection matrix. * small fix on RGCN. * Fix rgcn performance (#17) Co-authored-by: Ubuntu <ubuntu@ip-172-31-62-171.ec2.internal> * fix lint. * fix lint. * fix lint. * fix lint. * fix lint. * fix lint. * fix. * fix test. * fix lint. * test partitions. * remove redundant test for partitioning. * remove commented code. * fix partition. * fix tests. * fix RGCN. * fix test. * fix test. * fix test. * fix. * fix a bug. * update dmlc-core. * fix. * fix rgcn. * update readme. * add comments. Co-authored-by: Ubuntu <ubuntu@ip-172-31-2-202.us-west-1.compute.internal> Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-132.us-west-1.compute.internal> Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com> Co-authored-by: Ubuntu <ubuntu@ip-172-31-62-171.ec2.internal> * fix. * fix. * add div_int. * fix. * fix. * fix lint. * fix. * fix. * fix. * adjust. * move code. * handle heterograph. * return pytorch tensor in GPB. * remove some tests in example. * add to_block for distributed training. * use distributed to_block. * remove unnecessary function in DistGraph. * remove distributed to_block. * use pytorch tensor. * fix a bug in ntypes and etypes. * enable norm. * make the data loader compatible with the old format. * fix. * add comments. * fix a bug. * add test for heterograph. * support partition without reshuffle. * add test. * support partition without reshuffle. * fix. * add test. * fix bugs. * fix lint. * fix dataset. * fix for mxnet. * update docstring. * rename to floor_div * avoid exposing NodePartitionPolicy and EdgePartitionPolicy. * fix docstring. * fix error. * fixes. * fix comments. * rename. * rename. * explain IdMap. * fix docstring. * fix docstring. * update docstring. * remove the code of returning heterograph. * remove argument. * fix example. * make GraphPartitionBook an abstract class. * fix. * fix. * fix a bug. * fix a bug in example * fix a bug * reverse heterograph sampling. * temp fix. * fix lint. * Revert "temp fix." This reverts commit c450717b9f578b8c48769c675f2a19d6c1e64381. * compute norm. * Revert "reverse heterograph sampling." This reverts commit bd6deb7f52998de76508f800441ff518e2fadcb9. * fix. * move id_map.py * remove check * add more comments. * update docstring. Co-authored-by: Ubuntu <ubuntu@ip-172-31-2-202.us-west-1.compute.internal> Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-132.us-west-1.compute.internal> Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com> Co-authored-by: Ubuntu <ubuntu@ip-172-31-62-171.ec2.internal> | 25 January 2021, 03:18:00 UTC |
aa884d4 | Zihao Ye | 24 January 2021, 16:18:57 UTC | [doc][fix] Improve the docstring and fix its behavior in DGL's kernel (#2563) * upd * fix * lint * fix * upd | 24 January 2021, 16:18:57 UTC |
a6abffe | nv-dlasalle | 24 January 2021, 12:59:24 UTC | [Fix] Don't create extra formats in dataloader (#2551) Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 24 January 2021, 12:59:24 UTC |
2288098 | Quan (Andy) Gan | 24 January 2021, 04:44:54 UTC | [Feature] Converting a block to a graph and allow block construction (#2555) * first commit * more commit * fix and docstring * add to api reference * address comments * Update convert.py | 24 January 2021, 04:44:54 UTC |
7ff2662 | Mufei Li | 21 January 2021, 07:12:05 UTC | [Fix] Better Error Message for node_type_subgraph (#2554) * Update * Update * Update | 21 January 2021, 07:12:05 UTC |
9d90faf | nv-dlasalle | 21 January 2021, 03:12:30 UTC | Use ALG2 for SpMM in cuSparse (#2550) | 21 January 2021, 03:12:30 UTC |
2c6d071 | xnouhz | 20 January 2021, 17:33:30 UTC | [Feature] QM9 Dataset Support (#2521) * [Model] MixHop for Node Classification task * [docs] update * [docs] update * [fix] remove seed option * [fix] update readme * [feature] support qm9 dataset * [style] update * [docs] fix the details * [fix] indexing only support int * [style] update * [fix] multiple backends support * [docs] add qm9 * [fix] Z type: float32 -> int32 * [fix] Z type: int32 -> long * [docs] add ref * [docs] fix * [docs] update * [docs] update * [fix] test eval * [docs] fix example Co-authored-by: xnuohz@126.com <ubuntu@ip-172-31-44-184.us-east-2.compute.internal> Co-authored-by: Mufei Li <mufeili1996@gmail.com> Co-authored-by: Jinjing Zhou <VoVAllen@users.noreply.github.com> | 20 January 2021, 17:33:30 UTC |
0c15657 | Jinjing Zhou | 20 January 2021, 12:02:54 UTC | [Test] API benchmarks (#2542) * add bench jenkins * instance type * fix * fix * fix * 111 * test * 111 * 111 * fix * test * run * fix * fix * fix * fix * fix * publish results * 111 * regression * launch ec2 script * fix * add * run on master * change * rrr * run gpu * fix * fix * try fix * fix * ff * fix * fix * fix * refactor * fix * fix * update * fix * fix * fix * fix * remove import torchtext * add shm size * update * fix * fix * fix * fix * fix this!!!! * 111 * fix * remove verbose * fix * fix * fix * fix * fix * fix * fix * fix * update readme * fix * fix * fix * change asv default to head * commit sage and rgcn * fix * update * add benchmarks * add * fix * update * remove RandomState * tmp remove * new batch * fix * fix * fix * address comment * fix warning * fix Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 20 January 2021, 12:02:54 UTC |
8a2b54d | Josh Carty | 20 January 2021, 07:35:32 UTC | Add a TensorFlow example for SGC (#2480) This is a TensorFlow implementation of Simple Graph Convolution. For simplicity, we use the implementation of AdamW in TensorFlow Addons that differs from Adam in PyTorch. This results in worse performance on the evaluation datasets. Co-authored-by: Josh Carty <joshuac@spotify.com> Co-authored-by: Zihao Ye <expye@outlook.com> | 20 January 2021, 07:35:32 UTC |
917a755 | Jinjing Zhou | 19 January 2021, 11:35:43 UTC | [Fix] fix version check (#2544) | 19 January 2021, 11:35:43 UTC |
9a9a06e | 张天启 | 19 January 2021, 05:58:01 UTC | [Bug Fix] Fix undefined var bug in LegacyTUDataset (#2543) * [Bug Fix] Fix undefined var bug in LegacyTUDataset * upt * [Bug Fix] Fix cache file name bug in TUDataset Co-authored-by: Tong He <hetong007@gmail.com> | 19 January 2021, 05:58:01 UTC |
b36b6c2 | 张天启 | 18 January 2021, 09:01:52 UTC | [Example] Add HGP-SL example for pytorch backend (#2515) * add sagpool example for pytorch backend * polish sagpool example for pytorch backend * [Example] SAGPool: use std variance * [Example] SAGPool: change to std * add sagpool example to index page * add graph property prediction tag to sagpool * [Example] add graph classification example HGP-SL * [Example] fix sagpool * fix bug * [Example] change tab to space in README of hgp-sl * remove redundant files * remote redundant network * [Example]: change link from code to doc in HGP-SL * [Example] in HGP-SL, change to meaningful name * [Example] Fix path mistake for 'hardgat' Co-authored-by: zhangtianqi <tianqizh@amazon.com> | 18 January 2021, 09:01:52 UTC |
1caf01d | Minjie Wang | 18 January 2021, 06:28:22 UTC | Add one paper | 18 January 2021, 06:28:22 UTC |
6b46382 | Minjie Wang | 18 January 2021, 06:01:54 UTC | Update README.md | 18 January 2021, 06:01:54 UTC |
8c8c5b1 | Andrew | 17 January 2021, 02:32:47 UTC | [Bug fix] Stop erasing schemas of frames with no data rows (#2529) * added option for batching empty data, fixes #2526 * added option for batching empty data, fixes #2526 * decreased line lengths * removed trailing whitespace * fixed wrong feature name * [Bugfix] stop erasing schema of frames w/ no cols (fixes #2528) * removed arg doc Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com> Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> | 17 January 2021, 02:32:47 UTC |