PiRank: Learning To Rank via Differentiable Sorting

Cited by: 0|Bibtex|Views5
Other Links: arxiv.org

Abstract:

A key challenge with machine learning approaches for ranking is the gap between the performance metrics of interest and the surrogate loss functions that can be optimized with gradient-based methods. This gap arises because ranking metrics typically involve a sorting operation which is not differentiable w.r.t. the model parameters. Pri...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments