Personalized Multi-task Training for Recommender System

TL;DR

This paper introduces PMTRec, a novel personalized multi-task learning algorithm that improves recommender system accuracy by effectively integrating multiple information sources and dynamically balancing task contributions.

Contribution

It presents the first personalized multi-task learning method for RecSys, with modules for adaptive task weighting, gradient balancing, and task focusing, enhancing recommendation performance.

Findings

PMTRec outperforms existing multi-task learning methods on three real-world datasets.

Dynamic task weighting improves model adaptability to user/item variations.

Balanced training across tasks leads to more accurate personalized recommendations.

Abstract

In the vast landscape of internet information, recommender systems (RecSys) have become essential for guiding users through a sea of choices aligned with their preferences. These systems have applications in diverse domains, such as news feeds, game suggestions, and shopping recommendations. Personalization is a key technique in RecSys, where modern methods leverage representation learning to encode user/item interactions into embeddings, forming the foundation for personalized recommendations. However, integrating information from multiple sources to enhance recommendation performance remains challenging. This paper introduces a novel approach named PMTRec, the first personalized multi-task learning algorithm to obtain comprehensive user/item embeddings from various information sources. Addressing challenges specific to personalized RecSys, we develop modules to handle personalized task weights, diverse task orientations, and variations in gradient magnitudes across tasks. PMTRec dynamically adjusts task weights based on gradient norms for each user/item, employs a Task Focusing module to align gradient combinations with the main recommendation task, and uses a Gradient Magnitude Balancing module to ensure balanced training across tasks. Through extensive experiments on three real-world datasets with different scales, we demonstrate that PMTRec significantly outperforms existing multi-task learning methods, showcasing its effectiveness in achieving enhanced recommendation accuracy by leveraging multiple tasks simultaneously. Our contributions open new avenues for advancing personalized multi-task training in recommender systems.