March 1, 2020
In both mobile and web applications, speeding up user interface response times can often lead to significant improvements in user engagement. A common technique to improve responsiveness is to precompute data ahead of time for specific activities. However, simply precomputing data for all user and activity combinations is prohibitive at scale due to both network constraints and server-side computational costs. It is therefore important to accurately predict per-user application usage in order to minimize wasted precomputation (“predictive precompute”). In this paper, we describe the novel application of recurrent neural networks (RNNs) for predictive precompute. We compare their performance with traditional machine learning models, and share findings from their large-scale production use at Facebook. We demonstrate that RNN models improve prediction accuracy, eliminate most feature engineering steps, and reduce the computational cost of serving predictions by an order of magnitude.
Written by
Hanson Wang
Zehui Wang
Yuanyuan Ma
Research Topics
August 08, 2022
Ashkan Yousefpour, Akash Bharadwaj, Alex Sablayrolles, Graham Cormode, Igor Shilov, Ilya Mironov, Jessica Zhao, John Nguyen, Karthik Prasad, Mani Malek, Sayan Ghosh
August 08, 2022
December 06, 2018
Jeff Johnson
December 06, 2018
June 22, 2015
Nicolas Vasilache, Jeff Johnson, Michael Mathieu, Soumith Chintala, Serkan Piantino, Yann LeCun
June 22, 2015
December 07, 2018
December 07, 2018
September 01, 2020
Ashkan Yousefpour, Brian Q. Nguyen, Siddartha Devic, Guanhua Wang, Aboudy Kreidieh, Hans Lobel, Alexandre M. Bayen, Jason P. Jue
September 01, 2020
March 02, 2020
Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith
March 02, 2020
Foundational models
Latest news
Foundational models