PIFGSR: Pluggable framework for information fusion using generative artificial intelligence (GenAI) in recommender systems

Abstract

The application of Generative Artificial Intelligence (GenAI) in information fusion brings new breakthroughs in enhancing user experience within recommender systems, with sequential recommender being an indispensable element. Plugin-based diffusion models, a prominent GenAI approach, have proven effective in alleviating sparsity in sequential recommenders. However, by introducing disordered noise that disrupts sequential logic, these methods can distort user interest modeling and still struggle with data sparsity. To resolve these problems, we propose the novel general framework Pluggable Framework for Information Fusion Using Generative Artificial Intelligence (GenAI) in Recommender Systems..