dgl-ke icon indicating copy to clipboard operation
dgl-ke copied to clipboard

High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.

Results 60 dgl-ke issues
Sort by recently updated
recently updated
newest added

Thanks for your team's good work. But it's a pity that dgl-ke does not support dgl.heterograph. Do your team has a plan to support dgl 0.7? It will help us...

Hello, Thank you for the great work on this library. Currently it is my understanding that `dgl-ke` depends on a pinned version of the DGL backend (0.4.3). This unfortunately also...

The Python API is convenient for many use cases. It allows more customization and is very friendly for Jupyter Notebook users.

enhancement

In the triplet data loaders (utils.py:load_triplet_data and utils.py:load_raw_triplet_data) the imported data must be forced to be of type int64, to ensure that torch tensors are always long. Otherwise torch may...

Hello, I am trying to implement a dynamic knowledge graph (with the date as a property of the edges) on Trans-E. However, I can't find any paper that used DGL_KE...

*Description of changes:* There was a typo in the title of the page By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution,...

Hi, I would like to find the similarity scores of TransE, and I am finding the same error as this one [https://github.com/awslabs/dgl-ke/issues/160](url) ``` !DGLBACKEND=pytorch dglke_emb_sim --model_path ./wikimedia/TransE_l2_wikimedia_0/ \ --format 'h_*_*'...

I was trying the example "Knowledge Graph Embedding using the Wikimedia knowledge graph." and given that WikiMedia is a heterogeneous graph, the current notebook wont work since the EdgeSampler is...

I trained a TransE model and ran the following code snippet for the model prediction - **DGLBACKEND=pytorch dglke_predict --model_path ckpts/TransE_l1_JapEnc_2/ \ --format '*_r_t' --data_files data/rel.list data/tail.list \ --score_func logsigmoid --exec_mode...

I'm trying to run the training on FB15k dataset and I encountered this error. It would be great help if anyone could tell me what is going wrong here. Command:...