TransR
Tags: #machine learning #KGEquation
$$h_{r}=hM_{r}, t_{r}=tM_{r} \\f_{r}(h, t) = ||h_{r} + r - t_{r}||^{2}_{2}=||hM_{r}+r-tM_{r}||^{2}_{2}$$Latex Code
h_{r}=hM_{r}, t_{r}=tM_{r} \\f_{r}(h, t) = ||h_{r} + r - t_{r}||^{2}_{2}=||hM_{r}+r-tM_{r}||^{2}_{2}
Have Fun
Let's Vote for the Most Difficult Equation!
Introduction
Equation
Latex Code
h_{r}=hM_{r}, t_{r}=tM_{r} \\f_{r}(h, t) = ||h_{r} + r - t_{r}||^{2}_{2}=||hM_{r}+r-tM_{r}||^{2}_{2}
Explanation
TransR model learns low-dimensional representations of entities and relations to relation space r, and multiple original entity embedding to the mapping matrix M. See paper Learning Entity and Relation Embeddings for Knowledge Graph Completion for more details.
Reply