Explore the latest research from Meta

All Publications

September 4, 2022
Daniel Haimovich, Dima Karamshuk, Thomas Leeper, Evgeniy Riabenko, Milan Vojnovic

We propose a feature-based approach based on a self-excited Hawkes point process model, which involves prediction of the content’s popularity at one or more reference horizons in tandem with a point predictor of an effective growth parameter that reflects the timescale of popularity growth.

April 4, 2022
Assaf Eisenman, Kiran Kumar Matam, Steven Ingram, Dheevatsa Mudigere, Raghuraman Krishnamoorthi, Krishnakumar Nair, Misha Smelyanskiy, Murali Annavaram

We present Check-N-Run, a scalable checkpointing system for training large ML models at Facebook. While Check-N-Run is applicable to long running ML jobs, we focus on checkpointing recommendation models which are currently the largest ML models with Terabytes of model size. Check-N-Run uses two primary techniques to address the size and bandwidth challenges.

April 3, 2022
Ke Mao, Timotej Kapus, Lambros Petrou, Ákos Hajdu, Matteo Marescotti, Andreas Löscher, Mark Harman, Dino Distefano

We introduce FAUSTA, an algorithmic traffic generation platform that enables analysis and testing at scale. FAUSTA has been deployed at Meta to analyze and test the WhatsApp platform infrastructure since September 2020, enabling WhatsApp developers to deploy reliable code changes to a code base of millions of lines of code, supporting over 2 billion users who rely on WhatsApp for their daily communications.

February 14, 2022
Mahesh Balakrishnan, Chen Shen, Ahmed Jafri, Suyog Mapara, David Geraghty, Jason Flinn, Vidhya Venkat, Ivailo Nedelchev, Santosh Ghosh, Mihir Dharamshi, Jingming Liu, Filip Gruszczynski, Jun Li, Rounak Tibrewal, Ali Zaveri, Rajeev Nagar, Ahmed Yossef, Francois Richard, Yee Jiun Song

We built and deployed two production databases using Delos at Facebook, creating nine dierent log-structured protocols in the process.

January 22, 2022
Wenlei He, Julián Mestre, Sergey Pupyrev, Lei Wang, Hongtao Yu

In this paper we tackle the problem, which is also known as profile inference and profile rectification. We investigate the classical approach for profile inference, based on computing minimum-cost maximum flows in a control-flow graph, and develop an extended model capturing the desired properties of real-world profiles.