User behavior model development with private federated learning

• Main Authors: Durocher, Alexis Hugo Louis, Bhowmick, Abhishek, Duchi, John, Freudiger, Julien, Do, Thi Hai Van, Kalu, Kalu Onuka, Gopalan, Sowmya, Chatzidakis, Michael, Tartavel, Guillaume, Cosman, Stephen, Rogers, Ryan M, Kapoor, Gaurav, Jagadeesh, Vignesh, Araujo, Marcelo Lotif
• Format: Patent
• Language: English
• Published: 30.07.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

Embodiments described herein provide for a non-transitory machine-readable medium storing instructions to cause one or more processors to receive, at a client device, a machine learning model from a server, detect a usage pattern for a content item, store an association between the content item and the detected usage pattern in local data, train the machine learning model using local data for the content item with the detected usage pattern to generate a trained machine learning model, generate an update for the machine learning model, privatize the update for the machine learning model, and transmit the privatized update for the machine learning model to the server.