Da Zheng

it's most likely caused by pytorch. could you tell us what pytorch version you use. sourav1312 于 2021年3月6日周六 上午6:22写道： > I trained a TransE model and ran the following code...

can you try pytorch 1.6? this is the pytorch version we are using.

Thanks for your suggestions. We'll take a look at these models. We have plans to add GNN-based KGE models for knowledge graphs with node features.

For DGL, an undirected graph is stored as a bi-directional graph. If there is an edge from A to B, there will be an edge from B to A. In...

I think so. But it is also up to the model. Some of the KGE models, such as DistMult, are symmetric. For the symmetric models, I guess one direction is...

Yes, we plan to implement them. We have a prototype of DeepWalk and Metapath2vec, but haven't fully optimized them yet.

This is an interesting question. We never compare the two kinds of algorithms. KGE is supervised by link prediction while DeepWalk is random walk sequence. When we apply KGE on...

We don't have RGCN implementation in DGL-KE right now. We have one multi-GPU version in DGL: https://github.com/dmlc/dgl/blob/master/examples/pytorch/rgcn/entity_classify_mp.py. We'll have a distributed implementation very soon.

This is one of our motivations to create a Python API. It'll be great if you could contribute to this. Could you share such a script to us once you...

My understanding is that you like to contribute to creating a model class to evaluate pre-trained embeddings for various tasks: entity classification and link prediction. Is this right? We can...