Topic Replies Views Activity
Important Announcement: Deprecation of MXNet and TensorFlow Support in DGL 2.0
Questions

:loudspeaker: Important DGL Update: After DGL 2.0 (ETA: 2023Q4), we’ll be prioritizing PyTorch backend due to resource constraints, saying goodbye to MXNet and TensorFlow support. Don’t worry though – if you still need t…

1 80 August 23, 2023
Frequently Asked Questions (FAQ)
Questions

Are DGLGraphs directed or not? How to represent an undirected graph? All DGLGraphs are directed. To represent an undirected graph, you need to create edges for both directions. dgl.to_bidirected can be helpful, which…

2 8679 January 13, 2021
Training loop of GAT model for node regression task
Questions
0 6 September 22, 2023
How to obtain block and node features when iterating dataloader in minbatch training
Questions
0 13 September 21, 2023
Regression on vectors (list of predictions)
Questions
3 23 September 21, 2023
Split graph for train and test based on edge weight
Questions
1 36 September 21, 2023
Weave Lipophilicity model
Questions
1 32 September 20, 2023
Can DGL use pipeline parallelism?
Questions
11 135 September 20, 2023
Import dgl: ImportError (about dgl.dll)
Questions
1 39 September 19, 2023
Can DGL overlap sampling and computation When using GPU sampling?
Questions
1 44 September 19, 2023
Mini-batch training for model with aggregation of node features and edge features
Questions
1 33 September 18, 2023
DGL Readout Functions
Questions
1 22 September 18, 2023
FileNotFoundError: Cannot find DGL C++ sparse library 9/11
Questions
3 35 September 14, 2023
Question about negative sampling
Questions
1 56 September 14, 2023
Calculate bytes sent and received with communication time per machine in distributed training
Questions
1 35 September 14, 2023
Use graph-level features in node-level task
Models & Apps
1 28 September 13, 2023
Device API gpu is not enabled
Questions
5 9401 May 5, 2023
Sequential Graph Partition
Questions
2 57 September 8, 2023
dgl._ffi.base.DGLError:/dgl-0.5/src/array/cuda/array_op_impl.cu:252: Check failed: e == cudaSuccess || e == cudaErrorCudartUnloading: CUDA kernel launch error: no kernel image is available for execution on the device
Questions
2 65 September 7, 2023
Communication mechanism about DistDGL
Questions
3 50 September 7, 2023
Normalization in dgl package
Questions
1 34 September 7, 2023
GCN process Batched Graph
Questions
1 44 September 7, 2023
Get Original Node IDs from subgraph
Questions
3 82 September 6, 2023
How to make DGL heterogeneous graph?
Questions
2 47 September 4, 2023
Link prediction for new users
Questions
6 81 August 31, 2023
GNN for node regression task
Questions
5 75 August 30, 2023
Replace FFNN in GCN-FFNN model with other regressor
Questions
1 46 August 30, 2023
DGL metapath_reachable_graph: unable to allocate xxx GiB/TiB for an array with sahpe (xxxxxxxxxxxxxxxxx,) and data type int64
Questions
5 59 August 30, 2023
Why DGL is so memory-efficient compared to PyG
Questions
1 65 August 30, 2023
How to save the attention weight in official Hgt model example
Questions
3 71 August 30, 2023