Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation

TL;DR

This paper introduces GSERec, a graph-based method leveraging large language models and contrastive learning to improve search-enhanced recommendation for users with sparse search interactions, addressing data sparsity issues.

Contribution

The paper proposes GSERec, a novel approach that uses message passing on user-code graphs and contrastive loss to enhance recommendations for users with limited search data.

Findings

GSERec outperforms baselines on three real-world datasets.

Significant improvements for users with sparse search behaviors.

Effective use of LLM-generated codes for user similarity modeling.

Abstract

In modern online platforms, search and recommendation (S&R) often coexist, offering opportunities for performance improvement through search-enhanced approaches. Existing studies show that incorporating search signals boosts recommendation performance. However, the effectiveness of these methods relies heavily on rich search interactions. They primarily benefit a small subset of users with abundant search behavior, while offering limited improvements for the majority of users who exhibit only sparse search activity. To address the problem of sparse search data in search-enhanced recommendation, we face two key challenges: (1) how to learn useful search features for users with sparse search interactions, and (2) how to design effective training objectives under sparse conditions. Our idea is to leverage the features of users with rich search interactions to enhance those of users with sparse search interactions. Based on this idea, we propose GSERec, a method that utilizes message passing on the User-Code Graphs to alleviate data sparsity in Search-Enhanced Recommendation. Specifically, we utilize Large Language Models (LLMs) with vector quantization to generate discrete codes, which connect similar users and thereby construct the graph. Through message passing on this graph, embeddings of users with rich search data are propagated to enhance the embeddings of users with sparse interactions. To further ensure that the message passing captures meaningful information from truly similar users, we introduce a contrastive loss to better model user similarities. The enhanced user representations are then integrated into downstream search-enhanced recommendation models. Experiments on three real-world datasets show that GSERec consistently outperforms baselines, especially for users with sparse search behaviors.