Friend Bubbles: Enhancing Social Discovery on Facebook Reels
Mar 18, 2026Subasree Venkatsubhramaniyen, Joseph Asante, Jiayong Lin, Ramya Sai Mullapudi, Lechuan Li, Charles Yang, Arielle Ziv, Wanjun Wu, Aidan Toole

Summary
Introduced 'Friend Bubbles' to Facebook Reels, a system that highlights content friends have liked or reacted to. This involved developing user-user closeness models (survey-based and on-platform interaction-based) to identify relevant friends, and enhancing video ranking models with friend-bubble interaction signals and new tasks to incorporate relationship strength and learn downstream engagement. The system also optimized client-side performance by integrating friend-bubble metadata retrieval into the existing video prefetch work and conditionally disabling animations to maintain smooth scrolling and low latency.
More from the News Feed and Timeline Evolution trail
- A New Ranking Framework for Better Notification Quality on Instagram
- Inside Facebook’s video delivery system
- Improving Instagram notification management with machine learning and causal inference
- A linear programming approach for optimizing features in ML models
- How machine learning powers Facebook’s News Feed ranking algorithm