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

2025-08-06

AI Summary

In search-augmented recommendation, sparse user search behavior hinders effective representation learning and degrades model performance. Method: This paper proposes a knowledge transfer-based user graph collaborative learning framework. It first leverages search patterns from highly interactive users—encoded into discrete user codes via large language models and vector quantization—to construct a user-code graph. A message-passing mechanism over this graph enables cross-user propagation of search features, while contrastive learning precisely models user similarity. Contribution/Results: The approach effectively alleviates the bottleneck of insufficient search signals for sparse users. Extensive experiments on three real-world datasets demonstrate significant improvements over state-of-the-art baselines, particularly for users with limited search history, validating both efficacy and robustness.

Technology Category

• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Address sparse search data in search-enhanced recommendation systems
• Learn useful search features for users with sparse interactions
• Design effective training objectives under sparse conditions

Innovation

• Utilizes message passing on User-Code Graphs
• Leverages LLMs with vector quantization
• Introduces contrastive loss for user similarity