Hi, I wanted to say thank you for this intuitive presentation, I really appreciate it! I have been learning GNN for few months but It was not clear. Now it is!
First of all, thank you sir. You are doing a great job. But PLEASE sort your playlists. So if i want to watch them i know where to start and where to end. I think you have a great content which is not showing its best potential in youtube (YET) and it would be a great help if you just sort the playlists so that anyone could watch them in a sequence.
As always I recommend the original pre-print/paper of the relevant authors: Learning Entity and Relation Embeddings for Knowledge Graph Completion Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/view/9571/9523 where the authors describe "TransR" in detail (page 2183) and provide their source as stated in their abstract: "source code of this paper can be obtained from github.com/mrlyk423/relation_extraction"
Hi, I wanted to say thank you for this intuitive presentation, I really appreciate it! I have been learning GNN for few months but It was not clear. Now it is!
Really clear explanation, thanks
First of all, thank you sir. You are doing a great job. But PLEASE sort your playlists. So if i want to watch them i know where to start and where to end. I think you have a great content which is not showing its best potential in youtube (YET) and it would be a great help if you just sort the playlists so that anyone could watch them in a sequence.
Okay. Just create a new playlist for the T5 LLM videos and the GPT (ChatGPT) videos have now their own playlist. more to follow.
Can you mention coding part of TransR embedding of triple in python
As always I recommend the original pre-print/paper of the relevant authors:
Learning Entity and Relation Embeddings for Knowledge Graph Completion
Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence
www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/view/9571/9523
where the authors describe "TransR" in detail (page 2183) and
provide their source as stated in their abstract:
"source code of this paper can be obtained from
github.com/mrlyk423/relation_extraction"