Machine learning plays a key role in powering Twitter and our purpose of serving the public conversation. From onboarding people on the platform to connecting them with relevant conversations, we leverage machine learning (ML) across a multitude of our product surface areas.
To continually advance the state of machine learning, inside and outside Twitter, we are building out a research group at Twitter, led by Sandeep Pandey, to focus on a few key strategic areas such as natural language processing, reinforcement learning, ML ethics, recommendation systems, and graph deep learning.
We are excited to announce that, to help us get there, we have acquired Fabula AI (Fabula), a London-based start-up, with a world-class team of machine learning researchers who employ graph deep learning to detect network manipulation. Graph deep learning is a novel method for applying powerful ML techniques to network-structured data. The result is the ability to analyze very large and complex datasets describing relations and interactions, and to extract signals in ways that traditional ML techniques are not capable of doing.
This strategic investment in graph deep learning research, technology and talent will be a key driver as we work to help people feel safe on Twitter and help them see relevant information. Specifically, by studying and understanding the Twitter graph, comprised of the millions of Tweets, Retweets and Likes shared on Twitter every day, we will be able to improve the health of the conversation, as well as products including the timeline, recommendations, the explore tab and the onboarding experience.
Fabula was founded by Michael Bronstein, Damon Mannion, Federico Monti, and Ernesto Schmitt. It is led today by co-founder and chief scientist Michael Bronstein and chief technologist Federico Monti, who began their collaboration together while at the University of Lugano, Switzerland. Bronstein is one of the world’s leading researchers in graph deep learning, and has pioneered its application in the realm of Internet companies.
“We are really excited to join the ML research team at Twitter, and work together to grow their team and capabilities. Specifically, we are looking forward to applying our graph deep learning techniques to improving the health of the conversation across the service,” said Michael Bronstein.
Our initial focus when Fabula joins the Twitter team will be to improve the health of the conversation, with expanding applications to stop spam and abuse and other strategic priorities in the future.
Bronstein is currently the Chair in Machine Learning & Pattern Recognition at Imperial College, and will remain in that position while leading graph deep learning research at Twitter. Bronstein will be joined by long-time collaborators from academia (many current or former students) who have spent years researching advances in geometric deep learning.
Our acquisition of Fabula builds on other investments we’ve made in machine learning, for example, Madbits in 2014, Whetlab in 2015 and Magic Pony in 2016. Fabula's team will be joining the Twitter Cortex team of ML engineers, data scientists, and researchers. Cortex is the central ML org at Twitter with the goal to advance machine learning inside & outside Twitter.
We are excited to welcome the Fabula team to Twitter!