We call this a cross-entropy loss because it is derived from the standard
binary cross-entropy loss. Since we are feeding the output of the decoder to a
logistic function, we obtain normalized scores that are known as probabilities.

Cross-entropy with negative sampling

+ Here we are again comparing the decoded score for a true pair to a negative sample. However, rather than treating this as a binary classification task, in the equation below, we are just comparing the direct output of the decoders.
+ If the score for the “true” pair is more significant than the “negative” pair then we have a small loss. The ∆ term is called the margin, and the loss will equal 0 if the score difference is at least that large for all examples.
+ This loss is also known as the hinge loss.


Max-margin loss

+ Cross-entropy with negative sampling
+ Max-margin loss

Saint Olaf College

Graphical methods abstract the dependencies between entities, text and relations in the form of directed acyclic graphs, and then use inference models to identify the correct relations.

Graphical Methods 

Includes:
 + Node degree.
 + Node centrality.
 + The clustering coefficient.
 + Closed triangles, ego graphs, and motifs.



Learn Before

Related

Learn After