Multi-Selection for Recommendation Systems
Abstract
We present the construction of a multi-selection model to answer differentially private queries in the context of recommendation systems. The server sends back multiple recommendations and a ``local model'' to the user, which the user can run locally on its device to select the item that best fits its private features. We study a setup where the server uses a deep neural network (trained on the Movielens 25M dataset as the ground truth for movie recommendation. In the multi-selection paradigm, the average recommendation utility is approximately 97\% of the optimal utility (as determined by the ground truth neural network) while maintaining a local differential privacy guarantee with ranging around 1 with respect to feature vectors of neighboring users. This is in comparison to an average recommendation utility of 91\% in the non-multi-selection regime under the same constraints.
Cite
@article{arxiv.2504.07403,
title = {Multi-Selection for Recommendation Systems},
author = {Sahasrajit Sarmasarkar and Zhihao Jiang and Ashish Goel and Aleksandra Korolova and Kamesh Munagala},
journal= {arXiv preprint arXiv:2504.07403},
year = {2025}
}