A Survey on Point-of-Interest Recommendation: Models, Architectures, and Security

TL;DR

This survey comprehensively reviews recent advances in POI recommendation systems, focusing on models, architectures, and security, highlighting the transition from traditional to advanced techniques and addressing privacy and security challenges.

Contribution

It provides an up-to-date, systematic overview of POI recommendation models, architectures, and security considerations, including emerging trends like large language models and federated learning.

Findings

Transition from traditional to advanced models including large language models

Shift from centralized to decentralized and federated architectures

Increased focus on security and privacy-preserving approaches

Abstract

The widespread adoption of smartphones and Location-Based Social Networks has led to a massive influx of spatio-temporal data, creating unparalleled opportunities for enhancing Point-of-Interest (POI) recommendation systems. These advanced POI systems are crucial for enriching user experiences, enabling personalized interactions, and optimizing decision-making processes in the digital landscape. However, existing surveys tend to focus on traditional approaches and few of them delve into cutting-edge developments, emerging architectures, as well as security considerations in POI recommendations. To address this gap, our survey stands out by offering a comprehensive, up-to-date review of POI recommendation systems, covering advancements in models, architectures, and security aspects. We systematically examine the transition from traditional models to advanced techniques such as large language models. Additionally, we explore the architectural evolution from centralized to decentralized and federated learning systems, highlighting the improvements in scalability and privacy. Furthermore, we address the increasing importance of security, examining potential vulnerabilities and privacy-preserving approaches. Our taxonomy provides a structured overview of the current state of POI recommendation, while we also identify promising directions for future research in this rapidly advancing field.