1 code implementation • 21 Jan 2021 • Walker Ravina, Ethan Sterling, Olexiy Oryeshko, Nathan Bell, Honglei Zhuang, Xuanhui Wang, Yonghui Wu, Alexander Grushetsky
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 characteristics.
no code implementations • 6 May 2020 • Honglei Zhuang, Xuanhui Wang, Michael Bendersky, Alexander Grushetsky, Yonghui Wu, Petr Mitrichev, Ethan Sterling, Nathan Bell, Walker Ravina, Hai Qian
Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area.