Explore the latest research from Facebook

All Publications

December 7, 2020 Shali Jiang, Daniel Jiang, Max Balandat, Brian Karrer, Jacob R. Gardner, Roman Garnett
Paper

Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees

In this paper, we provide the first efficient implementation of general multi-step lookahead Bayesian optimization, formulated as a sequence of nested optimization problems within a multi-step scenario tree.
Paper
December 7, 2020 Maximilian Nickel, Brian Karrer, Daniel Jiang, Sam Daulton, Ben Letham, Andrew Gordon Wilson, Eytan Bakshy
Paper

BOTORCH: A Framework for Efficient Monte-Carlo Bayesian Optimization

We introduce BOTORCH, a modern programming framework for Bayesian optimization that combines Monte-Carlo (MC) acquisition functions, a novel sample average approximation optimization approach, auto-differentiation, and variance reduction techniques.
Paper
December 7, 2020 Riccardo Colini Baldeschi, Julian Mestre, Okke Schrijvers, Christopher A. Wilkens
Paper

The Ad Types Problem

In this paper we introduce the Ad Types Problem, a generalization of the traditional positional auction model for ad allocation that better captures some of the challenges that arise when ads of different types need to be interspersed within a user feed of organic content.
Paper
October 17, 2020 Justin Cheng, Moira Burke, Bethany de Gant
Paper

Country Differences in Social Comparison on Social Media

Social comparison is a common focus in discussions of online social media use and differences in its frequency, causes, and outcomes may arise from country or cultural differences. To understand how these differences play a role in experiences of social comparison on Facebook, a survey of 37,729 people across 18 countries was paired with respondents’ activity on Facebook.
Paper
October 9, 2020 Neta Barkay, Curtiss Cobb, Roee Eilat, Tal Galili, Daniel Haimovich, Sarah LaRocca, Katherine Morris, Tal Sarig
Paper

Weights and Methodology Brief for the COVID-19 Symptom Survey by University of Maryland and Carnegie Mellon University, in Partnership with Facebook

The Facebook company is partnering with academic institutions to support COVID-19 research and to help inform public health decisions. Currently, we are inviting Facebook app users in the United States to take a survey collected by faculty at Carnegie Mellon University (CMU) Delphi Research Center, and we are inviting Facebook app users in more than 200 countries or territories globally to take a survey collected by faculty at the University of Maryland (UMD) Joint Program in Survey Methodology.
Paper
September 22, 2020 Michael Bailey, Drew Johnston, Theresa Kuchler, Dominic Russel, Bogdan State, Johannes Stroebel
Paper

The Determinants of Social Connectedness in Europe

We use aggregated data from Facebook to study the structure of social networks across European regions.
Paper
August 27, 2020 Nima Noorshams, Saurabh Verma, Aude Hofleitner
Paper

TIES: Temporal Interaction Embeddings For Enhancing Social Media Integrity At Facebook

In this paper, we present our efforts to protect various social media entities at Facebook from people who try to abuse our platform. We present a novel Temporal Interaction EmbeddingS (TIES) model that is designed to capture rogue social interactions and flag them for further suitable actions. TIES is a supervised, deep learning, production ready model at Facebook-scale networks.
Paper
August 24, 2020 Viet-An Nguyen, Peibei Shi, Jagdish Ramakrishnan, Udi Weinsberg, Henry C. Lin, Steve Metz, Neil Chandra, Jane Jing, Dimitris Kalimeris
Paper

CLARA: Confidence of Labels and Raters

In this paper, we present CLARA (Confidence of Labels and Raters), a system developed and deployed at Facebook for aggregating reviewer decisions and estimating their uncertainty. We perform extensive validations and describe the deployment of CLARA for measuring the base rate of policy violations, quantifying reviewers’ performance, and improving their efficiency.
Paper
August 22, 2020 Julian Mestre, Nicolas Stier
Paper

Tight approximation for the minimum bottleneck generalized matching problem

We study a problem arising in statistical analysis called the minimum bottleneck generalized matching problem that involves breaking up a population into blocks in order to carry out generalizable statistical analyses of randomized experiments.
Paper
August 11, 2020 Eden Litt, Siyan Zhao, Robert Kraut, Moira Burke
Paper

What Are Meaningful Social Interactions in Today’s Media Landscape? A Cross-Cultural Survey

As we increasingly integrate technology into our lives, we need a better framework for understanding social interactions across the communication landscape. Utilizing survey data in which more than 4,600 people across the United States, India, and Japan described a recent social interaction, this article qualitatively and quantitatively explores what makes an interaction meaningful.
Paper