Details
-
New Feature
-
Status: To Do
-
Major
-
Resolution: Unresolved
-
None
Description
Currently MxNet implements only a few loss functions useful for neural information retrieval - in particular the Triplet Loss. In our recent research at Amazon we showed that this loss is not ideal for neural information retrieval settings and devise a new loss function which significantly outperformed Triplet Loss while improving training time by a factor of 10.
Relevant Paper: https://arxiv.org/abs/1905.12786 (Published at EMNLP 2019 - WNUT)
We would like to implement this as a loss function in Gluon to help any other people working on neural information retrieval systems using MxNet.
Attachments
Issue Links
- links to