Generative Multi-Target Cross-Domain Recommendation

2025-07-17

AI Summary

To address the challenges in multi-objective cross-domain recommendation—namely, the absence of shared entities across domains and heavy reliance on large-scale auxiliary data for pretraining—this paper proposes the first unified generative framework. It reformulates recommendation as a “next semantic identifier” generation task, where semantic identifiers—learned by a project tokenizer—serve as domain-agnostic knowledge mediators, enabling entity-alignment-free knowledge transfer. To jointly optimize multiple objectives, we introduce domain-aware contrastive learning and domain-adaptive fine-tuning. Extensive experiments on five public benchmarks demonstrate that our method significantly outperforms state-of-the-art baselines, especially in zero-entity-overlap scenarios, exhibiting superior generalization under low-resource conditions. This work establishes a novel generative paradigm for cross-domain recommendation.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Generation
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recently, there has been a surge of interest in Multi-Target Cross-Domain Recommendation (MTCDR), which aims to enhance recommendation performance across multiple domains simultaneously. Existing MTCDR methods primarily rely on domain-shared entities (eg users or items) to fuse and transfer cross-domain knowledge, which may be unavailable in non-overlapped recommendation scenarios. Some studies model user preferences and item features as domain-sharable semantic representations, which can be utilized to tackle the MTCDR task. Nevertheless, they often require extensive auxiliary data for pre-training. Developing more effective solutions for MTCDR remains an important area for further exploration. Inspired by recent advancements in generative recommendation, this paper introduces GMC, a generative paradigm-based approach for multi-target cross-domain recommendation. The core idea of GMC is to leverage semantically quantized discrete item identifiers as a medium for integrating multi-domain knowledge within a unified generative model. GMC first employs an item tokenizer to generate domain-shared semantic identifiers for each item, and then formulates item recommendation as a next-token generation task by training a domain-unified sequence-to-sequence model. To further leverage the domain information to enhance performance, we incorporate a domain-aware contrastive loss into the semantic identifier learning, and perform domain-specific fine-tuning on the unified recommender. Extensive experiments on five public datasets demonstrate the effectiveness of GMC compared to a range of baseline methods.

Problem

• Enhancing recommendation performance across multiple domains simultaneously
• Addressing non-overlapped scenarios without domain-shared entities
• Reducing reliance on extensive auxiliary data for pre-training

Innovation

• Generative model for multi-domain recommendation
• Semantic item identifiers unify cross-domain knowledge
• Domain-aware contrastive loss enhances performance