Stabilise learning to predict relations
jmsfltchr opened this issue · 1 comments
jmsfltchr commented
Problem to Solve
During relation prediction we see that the focus of the algorithm is to correctly classify all nodes and edges. Of these there are typically far more pre-existing nodes and edges that we don't care about than that we do.
Current Workaround
None
Proposed Solution
Possible options:
- Update the loss function of the learner
- Propagate preexistence through the neural network to reduce the burden on the network
- Filter out Unnecessary nodes in the decoder stage of the network, prior to calculating loss
- Reduce the number of output classes from
[preexists, does not exist, does exist]
to[does not exist, does exist]