Multi-Selection for Recommendation Systems
This addresses privacy concerns in recommendation systems for users by offering a method to maintain utility while protecting sensitive data, though it appears incremental as it builds on existing differential privacy techniques.
The paper tackled the problem of providing private recommendations by introducing a multi-selection model that allows users to locally select items based on private features, achieving approximately 97% of optimal utility compared to 91% in non-multi-selection methods under local differential privacy constraints with ε around 1.
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 $ε$ 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.