Predictive Precompute with Recurrent Neural Networks
This addresses the challenge of improving user interface response times for large-scale applications like Facebook, though it is incremental as it applies an existing method (RNNs) to a known bottleneck.
The paper tackled the problem of predicting per-user application usage to minimize wasted precomputation in mobile and web applications, demonstrating that RNN models improve prediction accuracy, eliminate most feature engineering, and reduce computational cost by an order of magnitude.
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.