Closed luoxc007 closed 4 months ago
dblp4HAN seems unavailable now and your suggestions sounds reasonable. Please use other datasets such as dblp4GTN, acm_han_raw, etc.
dblp4HAN seems unavailable now and your suggestions sounds reasonable. Please use other datasets such as dblp4GTN, acm_han_raw, etc.
I want to use dblp4GTN, but i meet a problem. The dataset 'acm4GTN' has the metapath embedding, such as 'pspap_m2v_emb' and so on. But i can not find the metapath embedding for dblp4GTN. On the other hand, i can use the dataset 'acm4GTN' in HGSL, but the dataset 'dblp4GTN' can not use in HGSL because of the reason i have told.
dblp4HAN seems unavailable now and your suggestions sounds reasonable. Please use other datasets such as dblp4GTN, acm_han_raw, etc.
I want to use dblp4GTN, but i meet a problem. The dataset 'acm4GTN' has the metapath embedding, such as 'pspap_m2v_emb' and so on. But i can not find the metapath embedding for dblp4GTN. On the other hand, i can use the dataset 'acm4GTN' in HGSL, but the dataset 'dblp4GTN' can not use in HGSL because of the reason i have told.
You are right. metapath2vec embedding is not available for dblp4GTN, one solution is to run metapath2vec on the dataset to generate the embedding and then assign it as node feature before running HGSL.
dblp4HAN seems unavailable now and your suggestions sounds reasonable. Please use other datasets such as dblp4GTN, acm_han_raw, etc.
I want to use dblp4GTN, but i meet a problem. The dataset 'acm4GTN' has the metapath embedding, such as 'pspap_m2v_emb' and so on. But i can not find the metapath embedding for dblp4GTN. On the other hand, i can use the dataset 'acm4GTN' in HGSL, but the dataset 'dblp4GTN' can not use in HGSL because of the reason i have told.
You are right. metapath2vec embedding is not available for dblp4GTN, one solution is to run metapath2vec on the dataset to generate the embedding and then assign it as node feature before running HGSL.
For example, you can modify the meta_path_key to APCPA in the config.ini file and then run the following command: python main.py -m Metapath2vec -t node_classification -d dblp4GTN -g -1 This will output the embeddings of authors in the output/metapath2vec directory.
Yeah, I get the 'APCPA' embeddings but the embedding's shape is (18405,128) which includes all nodes in dblp4GTN. Can the Metapath2vec generate target type node embedding or how to get the target type node embeddings from all the nodes embedding? What is the node order in the 'APCPA' embeddings, eg. author is range(0, 4057), conference is range(4057,4077) and paper is range(4077, 18405)?
Yeah, I get the 'APCPA' embeddings but the embedding's shape is (18405,128) which includes all nodes in dblp4GTN. Can the Metapath2vec generate target type node embedding or how to get the target type node embeddings from all the nodes embedding? What is the node order in the 'APCPA' embeddings, eg. author is range(0, 4057), conference is range(4057,4077) and paper is range(4077, 18405)?
@Zhanghyi
Yeah, I get the 'APCPA' embeddings but the embedding's shape is (18405,128) which includes all nodes in dblp4GTN. Can the Metapath2vec generate target type node embedding or how to get the target type node embeddings from all the nodes embedding? What is the node order in the 'APCPA' embeddings, eg. author is range(0, 4057), conference is range(4057,4077) and paper is range(4077, 18405)?
@Zhanghyi
The embedding file contains all node types in the same order as g.ntypes. We will update the relevant documentation for clarity.
Yeah, I get the 'APCPA' embeddings but the embedding's shape is (18405,128) which includes all nodes in dblp4GTN. Can the Metapath2vec generate target type node embedding or how to get the target type node embeddings from all the nodes embedding? What is the node order in the 'APCPA' embeddings, eg. author is range(0, 4057), conference is range(4057,4077) and paper is range(4077, 18405)?
@Zhanghyi
The embedding file contains all node types in the same order as g.ntypes. We will update the relevant documentation for clarity.
Thanks!
🐛 Bug
When I ran "python -u /home/wj/dgl/OpenHGNN-main/main.py -m HAN -d dblp4HAN -t node_classification -g 6 --use_best_config --load_from_pretrained" with openhgnn, I got an error as "UnboundLocalError: local variable '_dataset' referenced before assignment".
To Reproduce
Steps to reproduce the behavior:
1.Just run as the command I shown above.
Expected behavior
Environment
Additional context
None.