Ying-1106

Thank you for supporting OpenHGNN. We have not yet implemented RPDD & TRD in OpenHGNN, but we will implement it as soon as possible.

Thanks for supporting OpenHGNN.We have not yet implemented the content of the non_local part in FastGTN.We will follow up on this content in the future.

We have run 3 layers of GTN on our own computer and it can run normally. We speculate that your segment fault may be caused by insufficient graphics memory. Please...

this is the code about generating Dataset: base_dir = os.path.join(now_dir,'HGBl_base_dir') # construct the Ondiskdataset from existed dglgraph graph_file_path = '/data/zzh/TEST_DIR/HGBl_dir/HGBl-amazon_DGLGraph.bin' HGBl_Graph = dgl.load_graphs(filename=graph_file_path)[0][0] feature = HGBl_Graph.ndata['h'] product_feat_np = feature.numpy() product_feat_file...

> And please share which DGL version you're using. My DGL version is 2.2.1 + cu118

> Hello @Ying-1106, it'd be helpful if you can provide the error message. And you can try `print(train_set)` to examine the training set and check if data is correct. #...

> Hello @Ying-1106, it'd be helpful if you can provide the error message. And you can try `print(train_set)` to examine the training set and check if data is correct. #...

> how do you generate the `train_set`? are the Node IDs in each `seed` is edge type wised? # I generate train_set with 2 numpy files. One is edge type...

> In order to dive deep into the root cause, I recommend to narrow down the case with following suggestions. > > 1. does it crash on first iteration? >...