mirrors / dmlc--dgl

提交

提交图

  • 61fba9da0f [Doc] Add Node2Vec docstrings to documentation server (#3068) Quan (Andy) Gan 2021-06-29 22:29:10 +08:00
  • dad8751d29 [Doc] Add instructions for Windows users to install VC2015 redistributable (#3071) Quan (Andy) Gan 2021-06-29 13:10:48 +08:00
  • 02e5d47d2a [Example][Bugfix] Fix RGCN example datasplitting (#3037) nv-dlasalle 2021-06-28 19:16:28 -07:00
  • 2295c2186a [Benchmark] Add benchmark for GraphConv and HeteroGraphConv (#2999) Jinjing Zhou 2021-06-28 17:16:18 +08:00
  • 789b03f433 [Doc] Add KNN Benchmark Results (#3055) Tong He 2021-06-28 16:13:56 +08:00
  • 81456af8c5 [Doc] fix inconsistent variable names (#3065) Kay Liu 2021-06-28 13:30:08 +08:00
  • 7f4086da7a cuda() to to(device) (#3064) Tomohiro Endo 2021-06-28 12:56:24 +09:00
  • 2f43cdb3c8 deal with situation where num_layers equals 1 (#3066) WangYQ 2021-06-28 10:17:16 +08:00
  • 9664cdffd3 [Build] Make nccl optional (#3056) Jinjing Zhou 2021-06-27 22:36:01 +08:00
  • 115ac0b9a3 [Benchmark] Enable sample neighbors gpu benchmark (#3060) Jinjing Zhou 2021-06-25 14:24:01 +08:00
  • 427a5a96e0 [Doc] Update NodeDataLoader and EdgeDataLoader for GPU-based neighbor sampling (#3046) Quan (Andy) Gan 2021-06-25 10:46:21 +08:00
  • acd21a6d60 [Feature] Support direct creation from CSR and CSC (#3045) Quan (Andy) Gan 2021-06-25 10:05:47 +08:00
  • 2f7ca41459 [Bug fix] Use shared memory for grad sync when NCCL is not avaliable as PyTorch distributed backend. (#3034) xiang song(charlie.song) 2021-06-24 12:06:54 +08:00
  • 31f4483af7 add HAN sampling demo (#3005) maqy 2021-06-23 20:27:18 +08:00
  • e56bbafd25 [Feature] Biased Neighbor Sampling (#2987) Qidong Su 2021-06-23 17:44:51 +08:00
  • 7415eaa5fa [Bugfix] Handle case where process has no elements to update, in NCCL communicator (#3035) nv-dlasalle 2021-06-23 01:31:29 -07:00
  • cb2327d4a9 [Example] Fix error in gcn train due to missing argument (#3040) Tomohiro Endo 2021-06-23 16:50:07 +09:00
  • 5961c14026 [Doc] EdgeWeightNorm Fix doc (#3051) Tomohiro Endo 2021-06-23 16:49:31 +09:00
  • e667545da5 [Feature] Node2vec (#2992) Quan (Andy) Gan 2021-06-23 14:47:56 +08:00
  • 7359481497 [Feature][GPU] Add function for setting weights of a sparse embedding on multiple GPUs. (#3047) nv-dlasalle 2021-06-22 08:48:12 -07:00
  • 70af1945da [Doc] Add one paper to Awesome paper list (#3041) Xiangkun Hu 2021-06-22 18:43:55 +08:00
  • 1113f67422 [Kernel] Add heterograph support in CUDA kernels (SpMM, SDDMM) (#2925) Israt Nisa 2021-06-21 21:34:37 -04:00
  • ff519f98c3 [API] Standardize Subgraph APIs (#2929) Mufei Li 2021-06-21 19:53:37 +08:00
  • fc69f6ceca update two papers in awesome list (#3043) Tianjun Xiao 2021-06-21 13:14:25 +08:00
  • 9706eaa895 [Feature] add permission information and fix import problems (#3036) Kay Liu 2021-06-21 11:55:15 +08:00
  • e57c6e3506 [Fix] Fix lint resource usage & Fix Docs (#3032) Jinjing Zhou 2021-06-18 18:33:52 +08:00
  • 55e7796ac5 Revert "[Feature] add permission information and fix import problems (#2998)" (#3029) zhjwy9343 2021-06-17 13:58:38 +08:00
  • 7d069d62eb Add Ampere support to cmake files (#3031) nv-dlasalle 2021-06-16 12:57:28 -07:00
  • 7176f5f25f [Regression] Multigpu regression test (#2923) Jinjing Zhou 2021-06-16 18:37:59 +08:00
  • cba5b188b5 [Feature] add permission information and fix import problems (#2998) Kay Liu 2021-06-16 18:24:17 +08:00
  • aaec3d8a0b [Distributed] Support hierarchical partitioning (#3000) Da Zheng 2021-06-16 16:58:23 +08:00
  • 18eaad17cc fix bugs (#3008) Hengrui Zhang 2021-06-16 15:27:47 +08:00
  • 36c6c64957 Replace QM9_v2 with built-in QM9Edge Dataset (#3026) Hengrui Zhang 2021-06-16 14:35:40 +08:00
  • 305d5c16df [Example] update ogbn-arxiv and ogbn-proteins results (#3018) espylapiza 2021-06-16 13:33:43 +09:00
  • 8932285652 [bugfix] Fix sparse_optim when the state is stored on the CPU (fixes #2760) (#3013) nv-dlasalle 2021-06-15 11:37:32 -07:00
  • b4ad59d77f [Model] reformat and update performance of grace (#3009) Hengrui Zhang 2021-06-15 17:02:37 +08:00
  • 63aed58204 [Doc] Fix typo in DGL base dataset class (#2977) #3017 Leonardo Castorina 2021-06-15 09:15:52 +01:00
  • 64d0f3f355 [Feature] Add NN-descent support for the KNN graph function in dgl (#2941) Tianqi Zhang (张天启) 2021-06-15 14:25:02 +08:00
  • a303f07819 fix #2952 (#3010) Jinjing Zhou 2021-06-14 15:09:14 +08:00
  • 17141dd372 [Fix] Fix to_homo for graph with zero nodes ntype (#3011) Jinjing Zhou 2021-06-14 14:34:13 +08:00
  • 8b64ae59b8 [Performance] Perform to_block on the GPU when the dataloader is created with a GPU device. (#3016) nv-dlasalle 2021-06-13 03:51:00 -07:00
  • 79b057f0cf Fix example to test_acc is always computed at last epoch (#3014) nv-dlasalle 2021-06-12 18:02:00 -07:00
  • 2570d412f9 [NN] Add fast path for GateGCNConv when it has only one edge type (#2994) Jinjing Zhou 2021-06-12 01:13:18 +08:00
  • 411bef5498 [CPU, Parallel] parallel_for with default grain size (#3004) distgnn Tomasz Patejko 2021-06-11 11:09:30 +02:00
  • 17d604b5c7 [Feature] Allow using NCCL for communication in dgl.NodeEmbedding and dgl.SparseOptimizer (#2824) nv-dlasalle 2021-06-10 21:19:00 -07:00
  • 9497a9be85 [Bugfix][Examples] Fix graphsage multigpu training example training set size (#3002) nv-dlasalle 2021-06-10 16:35:08 -07:00
  • 5be937a7fb [Kernel] Slicing Batched Graphs (#2965) Mufei Li 2021-06-10 12:07:44 +08:00
  • ba1549244c [Performance][Kernel] Eliminating ctor&dtor zand IsNullArray overhead in random walks (#2990) Ajay Brahmakshatriya 2021-06-09 22:10:15 -04:00
  • f91a97d067 [Dataloader] Fix compatibility of DistributedSampler for older PyTorch versions (#2997) Quan (Andy) Gan 2021-06-09 20:14:26 +08:00
  • a7fe461c1c [Doc] Single-machine Multi-GPU node classification tutorial (#2976) Quan (Andy) Gan 2021-06-08 10:28:02 +08:00
  • 6c59fee99b [Model] HetGNN/GTN/HAN/NSHE/MAGNN examples (#2993) Theheavens 2021-06-08 08:54:27 +08:00
  • fd72df9a3d add Contrast-Reg to awesome papers (#2991) Tianjun Xiao 2021-06-07 14:43:12 +08:00
  • 972a9f1323 [Doc] Re-organize the code for dgl.geometry, and expose it in the doc (#2982) Tong He 2021-06-07 11:19:39 +08:00
  • e20d895324 [CPU Parallel] implementation of parallel_for with grain size (#2972) Tomasz Patejko 2021-06-06 15:09:24 +02:00
  • 895d6fff72 [Doc] changing of output dimension (#2981) Kay Liu 2021-06-05 22:12:41 +08:00
  • e2a28a6c8e [Doc] Revised Two Issues in Message Passing Tutorial (#2983) Kay Liu 2021-06-05 18:54:31 +08:00
  • 849cbec6ee [Feature] add positive negative statistics (#2984) Kay Liu 2021-06-05 15:48:11 +08:00
  • 6e9d16459e [Fix] Fixed AttributeError with new version of torchtext (0.9+). (#2985) Alex P 2021-06-04 20:01:20 +02:00
  • b1628f2398 [Tutorial] Distributed node classification. (#2969) Da Zheng 2021-06-04 21:50:16 +08:00
  • 6a56562a7c [CI] Use k8s cluster (#2957) Jinjing Zhou 2021-06-04 18:31:11 +08:00
  • 2df4a95f3e [Feature] Make to_heterogeneous(to_homogeneous(hg)) return hg (#2958) Quan (Andy) Gan 2021-06-03 18:50:18 +08:00
  • 60426278bf [Example] TAHIN (#2864) KounianhuaDu 2021-06-03 16:03:55 +08:00
  • 7e58236cc7 [Build] Fix NCCL building crashes when using submodules but with system NCCL installed (#2975) Quan (Andy) Gan 2021-06-03 14:41:52 +08:00
  • 75ec58260a Add heterograph support in C kernels (#2882) Israt Nisa 2021-06-03 00:14:25 -04:00
  • 6383e64937 [Doc] correct the matrix multiplication symbols (#2961) Kay Liu 2021-06-03 08:51:23 +08:00
  • 7a816f4743 [Doc] Minor fix on the distributed training doc. (#2968) Da Zheng 2021-06-02 18:46:52 +08:00
  • f8d6bf8e07 [Test] Fix regression ram info (#2964) Jinjing Zhou 2021-06-02 16:14:05 +08:00
  • 0e964ea566 increase timeout for dgl.nn.NodeEmbedding TCPStore get/wait to 10 minutes (#2967) Soji Adeshina 2021-06-01 23:56:42 -07:00
  • 2ae190d690 [Doc] fix shape mismatch problem in user guide (#2938) Quan (Andy) Gan 2021-06-02 12:18:10 +08:00
  • 527bbfa8ea update nightly installation (#2959) Quan (Andy) Gan 2021-06-02 12:12:01 +08:00
  • 22d0df8b6a [Doc] Update link_predict.py docstring (#2960) Moritz Blum 2021-06-02 06:08:28 +02:00
  • 86ba2335c3 [Testing] Enable C++ tests on GPU (#2945) nv-dlasalle 2021-06-01 11:39:57 -07:00
  • b8fe2b4837 [Feature][Sampler] Sort CSR by tag (#1664) Qidong Su 2021-06-01 23:33:56 +08:00
  • 0437b16497 [Doc] Fix a typo in the tutorial for Neighbor Sampling (#2935) Chuang, Yun-Shiuan 2021-06-01 00:59:22 -05:00
  • fcfe52aee5 fix residual (#2962) Quan (Andy) Gan 2021-06-01 13:50:39 +08:00
  • 2ad7a9e9dd [Fix] Fix #2808 (#2917) Jinjing Zhou 2021-05-31 19:05:58 +08:00
  • 09642d7c21 [Tutorial] Single Machine Multi-GPU Minibatch Graph Classification (#2940) Mufei Li 2021-05-31 18:36:34 +08:00
  • 9a0e13ac61 Speed up random number generation. (#2953) Da Zheng 2021-05-28 19:17:53 +08:00
  • b8b0fd22b2 [Feature] add two fraud datasets (#2908) Kay Liu 2021-05-28 15:45:44 +08:00
  • 64d2a2aff7 [Feature] fix #2876, add two fake news datasets (#2939) Kay Liu 2021-05-28 14:29:26 +08:00
  • 18dbaebebc [Distributed] Specify the graph format for distributed training (#2948) Da Zheng 2021-05-26 18:09:30 +08:00
  • 1db4ad4fcc Move pointer dereferencing in CDFSampler::draw() and AliasSampler::draw() to inside of conditional (#2943) nv-dlasalle 2021-05-24 22:53:53 -07:00
  • 66eb240d15 [Bugfix] Include NCCL as a submodule (#2934) nv-dlasalle 2021-05-24 18:46:16 -07:00
  • 06b9ec2e8e [Doc] Add two papers to awesome paper list (#2936) Xiangkun Hu 2021-05-24 14:38:12 +08:00
  • c46602d7d8 [Doc] Fix a typo in the tutorial for link prediction (#2928) Chuang, Yun-Shiuan 2021-05-23 09:43:45 -05:00
  • ae8dbe6d3c [Feature][Performance] Implement NCCL wrapper for communicating NodeEmbeddings and sparse gradients. (#2825) nv-dlasalle 2021-05-20 10:58:17 -07:00
  • 0e9259b472 Add ED-GNN to Awesome Papers in DGL. (#2903) xiang song(charlie.song) 2021-05-20 12:05:06 +08:00
  • 5d7e80f413 [Feature] Add bruteforce implementation for KNN with O(Nk) space complexity (#2892) Tianqi Zhang (张天启) 2021-05-19 18:27:43 +08:00
  • db0fb4eaef Update README.md (#2927) Mufei Li 2021-05-19 15:45:07 +08:00
  • 1968adbaf7 Update README.md (#2924) Quan (Andy) Gan 2021-05-19 15:18:39 +08:00
  • 6e7f19f27b [Distributed] add distributed in-degree and out-degree. (#2918) Da Zheng 2021-05-18 19:46:09 +08:00
  • 50492d56a8 Fixing issue #2921 (#2922) V.E 2021-05-18 03:54:38 +02:00
  • c018436588 [Example] add latent dirichlet allocation (#2883) yifeim 2021-05-17 05:25:36 -07:00
  • 657c220de7 [Feature] Python interface for adjacency matrix summation and multiplication (#2893) Quan (Andy) Gan 2021-05-17 19:47:02 +08:00
  • 29fec7d5db Update README.md (#2920) Mufei Li 2021-05-17 17:30:26 +08:00
  • 7c7113f660 add use_ddp to dataloaders (#2911) Quan (Andy) Gan 2021-05-17 15:46:02 +08:00
  • b03077b60d [NN] GCNII model added <https://arxiv.org/pdf/2007.02133.pdf> (#2874) kyawlinoo 2021-05-17 04:25:59 +02:00
  • ac1536cf92 [Feature] add udf support for cross_reducer (#2891) Secbone 2021-05-15 14:00:37 +08:00
  • 9983107384 [Feature] Support multidimensional features for GAT (#2912) Quan (Andy) Gan 2021-05-15 02:47:23 +08:00
  • caa6d6072c [Feature] Replacing thread_wrapped_func with minimal mp.Process wrapper (#2905) Quan (Andy) Gan 2021-05-14 11:34:49 +08:00