Intellectual Property India Publishes Patent Application for 'Federated Learning System For Privacy-Preserving Personalized Recommendations' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123258 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 6, 2025, for 'federated learning system for privacy-preserving personalized recommendations.'

Inventor(s) include Dr. Debi Prasanna Acharjya; Mr. Abhigyan Pal; and Ms. Aparna Sinha.

The application for the patent was published on Jan. 2, under issue no. 01/2026.

According to the abstract released by the Intellectual Property India: "The present disclosure provides a computer-implemented method for privacy-preserving personalized recommendation using federated learning. The method includes distributing a global recommendation model from a central server to client devices (FIG. 1), performing local training on each device using locally stored user interaction data to generate updated model parameters without transmitting user data to the central server, transmitting updated parameters from client devices to the central server, aggregating received parameters at the central server to generate an improved global model, redistributing the improved model to client devices, and iterating these steps through multiple rounds. The system includes client devices with local data stores and model trainers, and a central server with model aggregation capabilities, wherein communication occurs through secure parameter exchange while maintaining user data privacy through local computation."

Disclaimer: Curated by HT Syndication.