5 citations · 5 across the 2 of their papers we have counts for
3 papers
Distilling Interpretable Models into Human-Readable Code
Walker Ravina, Ethan Sterling, Olexiy Oryeshko +5
The goal of model distillation is to faithfully transfer teacher model knowledge to a model which is faster, more generalizable, more interpretable, or possesses other desirable ch…
Interpretable Learning-to-Rank with Generalized Additive Models
Honglei Zhuang, Xuanhui Wang, Michael Bendersky +7
Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating…
TF Boosted Trees: A scalable TensorFlow based framework for gradient boosting
Natalia Ponomareva, Soroush Radpour, Gilbert Hendry +4
TF Boosted Trees (TFBT) is a new open-sourced frame-work for the distributed training of gradient boosted trees. It is based on TensorFlow, and its distinguishing features include…