Heterogeneous Knowledge Fusion: A Novel Approach for Personalized Recommendation via LLM
This addresses the challenge of integrating diverse user behavior data for personalized recommendations, though it appears incremental as it builds on existing LLM methods.
The paper tackles the problem of feature sparsity and knowledge fragmentation in recommendation systems by proposing a novel approach that uses Large Language Models (LLMs) to extract and fuse heterogeneous knowledge from user behavior, combined with instruction tuning, which significantly improves recommendation performance.
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.