MultiHead MultiModal Deep Interest Recommendation Network

TL;DR

This paper introduces a multi-head multi-modal extension to the DIN recommendation model, enriching feature utilization and improving prediction accuracy by leveraging diverse data sources and advanced neural network modules.

Contribution

It proposes a novel multi-head multi-modal DIN model that enhances feature richness and cross-modal interactions for better recommendation performance.

Findings

Improved recommendation prediction accuracy.

Outperforms state-of-the-art methods on multiple metrics.

Enriches feature sets with multi-modal data.

Abstract

With the development of information technology, human beings are constantly producing a large amount of information at all times. How to obtain the information that users are interested in from the large amount of information has become an issue of great concern to users and even business managers. In order to solve this problem, from traditional machine learning to deep learning recommendation systems, researchers continue to improve optimization models and explore solutions. Because researchers have optimized more on the recommendation model network structure, they have less research on enriching recommendation model features, and there is still room for in-depth recommendation model optimization. Based on the DIN\cite{Authors01} model, this paper adds multi-head and multi-modal modules, which enriches the feature sets that the model can use, and at the same time strengthens the cross-combination and fitting capabilities of the model. Experiments show that the multi-head multi-modal DIN improves the recommendation prediction effect, and outperforms current state-of-the-art methods on various comprehensive indicators.