Publication

Behavioural and Structural Imitation Models in Facebook’s WW Simulation System

International Workshop on Realizing Artificial Intelligence Synergies in Software Engineering (RAISE)


Abstract

We describe Facebook’s development of WW, its cyber-cyber digital twin, and, in particular, the way it uses hybrid artificial intelligence techniques for behavioral and structural imitation. WW is a simulation of Facebook user behavior on the real Facebook platform, which Facebook uses to test and optimize its products. There are inherently many foundational scientific challenges that come to the fore when attempting to safely, reliably and effectively simulate user behaviors at scale. This paper outlines some existing practical and scientific work at Facebook, together with open problems and challenges for this research agenda, which lies at the intersection of artificial intelligence and software engineering.

Related Publications

All Publications

ISAAC - December 5, 2021

On the Extended TSP Problem

Julián Mestre, Sergey Pupyrev, Seeun William Umboh

ICML - July 24, 2021

Ditto: Fair and Robust Federated Learning Through Personalization

Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith

ESEM - September 23, 2021

Measurement Challenges for Cyber Cyber Digital Twins: Experiences from the Deployment of Facebook’s WW Simulation System

Kinga Bojarczuk, Inna Dvortsova, Johann George, Natalija Gucevska, Mark Harman, Maria Lomeli, Simon Mark Lucas, Erik Meijer, Rubmary Rojas, Silvia Sapora

Federated Learning for User Privacy and Data Confidentiality Workshop At ICML - July 24, 2021

Federated Learning with Buffered Asynchronous Aggregation

John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Michael Rabbat, Mani Malek, Dzmitry Huba

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy