FedPOIRec: Privacy Preserving Federated POI Recommendation with Social Influence

TL;DR

FedPOIRec is a federated learning framework for POI recommendation that preserves user privacy, incorporates social influence, and achieves comparable accuracy to centralized methods with low overhead.

Contribution

This work introduces FedPOIRec, a novel privacy-preserving federated learning approach that integrates social influence for improved POI recommendations.

Findings

Achieves recommendation quality comparable to centralized systems.

Incorporates social influence with low computational and communication overhead.

Utilizes homomorphic encryption for privacy-preserving social data integration.

Abstract

With the growing number of Location-Based Social Networks, privacy preserving location prediction has become a primary task for helping users discover new points-of-interest (POIs). Traditional systems consider a centralized approach that requires the transmission and collection of users' private data. In this work, we present FedPOIRec, a privacy preserving federated learning approach enhanced with features from users' social circles for top-$N$ POI recommendations. First, the FedPOIRec framework is built on the principle that local data never leave the owner's device, while the local updates are blindly aggregated by a parameter server. Second, the local recommenders get personalized by allowing users to exchange their learned parameters, enabling knowledge transfer among friends. To this end, we propose a privacy preserving protocol for integrating the preferences of a user's friends after the federated computation, by exploiting the properties of the CKKS fully homomorphic encryption scheme. To evaluate FedPOIRec, we apply our approach into five real-world datasets using two recommendation models. Extensive experiments demonstrate that FedPOIRec achieves comparable recommendation quality to centralized approaches, while the social integration protocol incurs low computation and communication overhead on the user side.