SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911583855181824 |
|---|---|
| author | Zhang, Chunxu Huang, Shanqiang Zhang, Zijian Liu, Jiahong Yu, Linsong Wan, Ruiqi Yang, Bo King, Irwin |
| author_facet | Zhang, Chunxu Huang, Shanqiang Zhang, Zijian Liu, Jiahong Yu, Linsong Wan, Ruiqi Yang, Bo King, Irwin |
| contents | Cross-domain recommendation (CDR) addresses the data sparsity and cold-start problems in the target domain by leveraging knowledge from data-rich source domains. However, existing CDR methods often rely on domain-specific features or identifiers that lack transferability across different domains, limiting their ability to capture inter-domain semantic patterns. To overcome this, we propose SemaCDR, a semantics-driven framework for cross-domain sequential recommendation that leverages large language models (LLMs) to construct a unified semantic space. SemaCDR creates multiview item features by integrating LLM-generated domain-agnostic semantics with domain-specific content, aligned by contrastive regularization. SemaCDR systematically creates LLM-generated domain-specific and domain-agnostic semantics, and employs adaptive fusion to generate unified preference representations. Furthermore, it aligns cross-domain behavior sequences with an adaptive fusion mechanism to synthesize interaction sequences from source, target, and mixed domains. Extensive experiments on real-world datasets show that SemaCDR consistently outperforms state-of-the-art baselines, demonstrating its effectiveness in capturing coherent intra-domain patterns while facilitating knowledge transfer across domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09551 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation Zhang, Chunxu Huang, Shanqiang Zhang, Zijian Liu, Jiahong Yu, Linsong Wan, Ruiqi Yang, Bo King, Irwin Information Retrieval Artificial Intelligence Cross-domain recommendation (CDR) addresses the data sparsity and cold-start problems in the target domain by leveraging knowledge from data-rich source domains. However, existing CDR methods often rely on domain-specific features or identifiers that lack transferability across different domains, limiting their ability to capture inter-domain semantic patterns. To overcome this, we propose SemaCDR, a semantics-driven framework for cross-domain sequential recommendation that leverages large language models (LLMs) to construct a unified semantic space. SemaCDR creates multiview item features by integrating LLM-generated domain-agnostic semantics with domain-specific content, aligned by contrastive regularization. SemaCDR systematically creates LLM-generated domain-specific and domain-agnostic semantics, and employs adaptive fusion to generate unified preference representations. Furthermore, it aligns cross-domain behavior sequences with an adaptive fusion mechanism to synthesize interaction sequences from source, target, and mixed domains. Extensive experiments on real-world datasets show that SemaCDR consistently outperforms state-of-the-art baselines, demonstrating its effectiveness in capturing coherent intra-domain patterns while facilitating knowledge transfer across domains. |
| title | SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2604.09551 |