A Multi-Modal Latent-Features based Service Recommendation System for the Social Internet of Things

TL;DR

The paper tackles the challenge of delivering accurate service recommendations in the Social Internet of Things (SIoT), where data are heterogeneous and sparse. It introduces MMRS, a latent-based framework that learns item-item structures from multi-modal features using a KNN modality-aware graph, aggregates them into a unified latent graph, and applies graph convolutions to inject high-order affinities, which are then integrated with collaborative filtering via a Bayesian Personalized Ranking objective. The approach is validated on real-world, multi-modal Amazon datasets, showing that MMRS outperforms state-of-the-art SIoT recommenders and demonstrates robustness in cold-start scenarios. The work advances SIoT service recommendation by effectively modeling latent item relationships across modalities and providing scalable, personalized, context-aware recommendations with practical implications for industrial, security, smart-city, and healthcare deployments.

Abstract

The Social Internet of Things (SIoT), is revolutionizing how we interact with our everyday lives. By adding the social dimension to connecting devices, the SIoT has the potential to drastically change the way we interact with smart devices. This connected infrastructure allows for unprecedented levels of convenience, automation, and access to information, allowing us to do more with less effort. However, this revolutionary new technology also brings an eager need for service recommendation systems. As the SIoT grows in scope and complexity, it becomes increasingly important for businesses and individuals, and SIoT objects alike to have reliable sources for products, services, and information that are tailored to their specific needs. Few works have been proposed to provide service recommendations for SIoT environments. However, these efforts have been confined to only focusing on modeling user-item interactions using contextual information, devices' SIoT relationships, and correlation social groups but these schemes do not account for latent semantic item-item structures underlying the sparse multi-modal contents in SIoT environment. In this paper, we propose a latent-based SIoT recommendation system that learns item-item structures and aggregates multiple modalities to obtain latent item graphs which are then used in graph convolutions to inject high-order affinities into item representations. Experiments showed that the proposed recommendation system outperformed state-of-the-art SIoT recommendation methods and validated its efficacy at mining latent relationships from multi-modal features.

Figures (10)

• Figure 1: multi-modal generated data in SIoT environment.
• Figure 2: Item-item learning structure of data exchanged between SIoT devices
• Figure 3: Latent structure exploration for tailored recommendation in SIoT environment
• Figure 4: Recommendation Process.
• Figure 5: RMSE and MAE values for Top-5 recommendation list