Heterogeneous Knowledge Fusion: A Novel Approach for Personalized Recommendation via LLM

TL;DR

This paper introduces a novel method that leverages Large Language Models to fuse heterogeneous user behavior data, effectively addressing feature sparsity and knowledge fragmentation to enhance personalized recommendation accuracy.

Contribution

It proposes a new approach that extracts and fuses heterogeneous knowledge from user behaviors using LLMs, with instruction tuning for personalized recommendations.

Findings

Effective integration of heterogeneous user behavior data.

Significant improvement in recommendation performance.

Addresses feature sparsity and knowledge fragmentation issues.

Abstract

The analysis and mining of user heterogeneous behavior are of paramount importance in recommendation systems. However, the conventional approach of incorporating various types of heterogeneous behavior into recommendation models leads to feature sparsity and knowledge fragmentation issues. To address this challenge, we propose a novel approach for personalized recommendation via Large Language Model (LLM), by extracting and fusing heterogeneous knowledge from user heterogeneous behavior information. In addition, by combining heterogeneous knowledge and recommendation tasks, instruction tuning is performed on LLM for personalized recommendations. The experimental results demonstrate that our method can effectively integrate user heterogeneous behavior and significantly improve recommendation performance.