MAInt: A multi-task learning model with automatic feature interaction learning for personalized recommendations

Abstract

Nowadays, more and more recommender systems apply multi-task learning to provide users with more accurate personalized recommendations. However, most of the existing multi-task learning models ignore the importance of explicit feature interactions in different tasks, which are an important part of recommender system models. In addition, the knowledge sharing mechanism of the existing model is difficult to meet the needs of all tasks, resulting in the performance degradation of some tasks. To address these issues, we propose a Multi-task learning model based on Automatic feature Interaction learning (MAInt). The Tasks Interaction Layer in MAInt automatically learns explicit feature interactions in different tasks through self-attention neural networks. At the same time, this process allows each task to interact with each other, so that each task can adaptively extract helpful information from other task features. We conducted multiple experiments on two popular public datasets: Census-income Dataset and Ali-CCP Dataset, and the experimental results verified the effectiveness of our proposed model.