Generative Retrieval With Semantic Tree-structured Item Identifiers Via Contrastive Learning

Abstract

The retrieval phase is a vital component in recommendation systems, requiring the model to be effective and efficient. Recently, generative retrieval has become an emerging paradigm for document retrieval, showing notable performance. These methods enjoy merits like being end-to-end differentiable, suggesting their viability in recommendation. However, these methods fall short in efficiency and effectiveness for large-scale recommendations. To obtain efficiency and effectiveness, this paper introduces a generative retrieval framework, namely SEATER, which learns SEmAntic Tree-structured item identifiERs via contrastive learning. Specifically, we employ an encoder-decoder model to extract user interests from historical behaviors and retrieve candidates via tree-structured item identifiers. SEATER devises a balanced k-ary tree structure of item identifiers, allocating semantic space to each token individually. This strategy maintains semantic consistency within the same level, while dist

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keysi2023generative

Related papers

• Efficient Optimization Of Hierarchical Identifiers For Generative Recommendation (2025)1.91
• Cost: Contrastive Quantization Based Semantic Tokenization For Generative Recommendation (2024)7.81
• Generative Retrieval As Multi-vector Dense Retrieval (2024)8.60
• Generative Retrieval Meets Multi-graded Relevance (2024)2.26
• CAT-ID\(^2\): Category-tree Integrated Document Identifier Learning For Generative Retrieval In E-commerce (2025)0.00
• SEMINAR: Search Enhanced Multi-modal Interest Network And Approximate Retrieval For Lifelong Sequential Recommendation (2024)0.00
• Unified Semantic And ID Representation Learning For Deep Recommenders (2025)0.00
• Sparse Meets Dense: Unified Generative Recommendations With Cascaded Sparse-dense Representations (2025)0.00