1 code implementation • 16 Mar 2022 • Yi Ding, Avinash Rao, Hyebin Song, Rebecca Willett, Henry Hoffmann
To predict stragglers accurately and early without labeled positive examples or assumptions on latency distributions, this paper presents NURD, a novel Negative-Unlabeled learning approach with Reweighting and Distribution-compensation that only trains on negative and unlabeled streaming data.