Goto

Collaborating Authors

 Technology


Pseudo codes

Neural Information Processing Systems

Note that we don't validate the inner-loop'sฮป at every outer-loop iteration, but keep changing it on-the-fly at each validation cycle.






Learning from Both Structural and Textual Knowledge for Inductive Knowledge Graph Completion

Neural Information Processing Systems

In this paper, we propose a two-stage framework that imposes both structural and textual knowledge to learn rule-based systems. In the first stage, we compute a set of triples with confidence scores (called soft triples) from a text corpus by distant supervision, where a textual entailment model with multi-instance learning is exploited to estimate whether a given triple is entailed by a set of sentences. In the second stage, these soft triples are used to learn a rule-based model for KGC.



Gradient-basedEditingofMemoryExamplesfor Online Task-freeContinualLearning

Neural Information Processing Systems

GMED-editedexamplesremain similar to their unedited forms, but can yield increased loss in the upcoming model updates, thereby making thefuture replays more effectiveinovercoming catastrophic forgetting.