search

hwwang55 / PathCon

Combining relational context and relational paths for knowledge graph completion
MIT License
131 stars 29 forks source link

Inductive KG completion #7

Open Nikis14 opened 3 years ago

Nikis14 commented 3 years ago

Hi there! Can you help me with the question about using the model in an inductive setting, please?

Let's assume, we want to get the model scores for a pair of vertices not presented in training set. According to the code, we need to use calculated relational paths which rely only on the training set. It means that for new vertices there will be no paths connecting them with vertices in the training set. What should we do in such a case?

kalinin-sanja commented 3 years ago

Hi there! Can you help me with the question about using the model in an inductive setting, please?

Let's assume, we want to get the model scores for a pair of vertices not presented in training set. According to the code, we need to use calculated relational paths which rely only on the training set. It means that for new vertices there will be no paths connecting them with vertices in the training set. What should we do in such a case?

Hey! Your question is related to mine: https://github.com/hyren/PathCon/issues/1#issue-732365218. But I still haven't received a response from the authors.