AI 中文总结
ATLAS是一种多源推荐域泛化框架，无需目标域适配或LLM预训练，可从异构源域学习域不变表示，在未见域零样本推荐中优于多种基线，HitRate平均提升24%。
AI 中文摘要
推荐系统仍存在域绑定问题：在一个交互环境中训练的模型，通常需要重新训练或目标域适配，才能在新目录上运行。在电影领域训练的推荐模型，无法直接部署来推荐杂货或电子游戏。现有方法通过迁移受限形式的推荐知识、适配目标域，或利用大语言模型（LLM）获取可迁移表示来缓解该问题。我们转而研究：仅从多个异构域学习的推荐特定知识，能否在无需目标域适配或语言模型预训练的情况下，泛化到完全未见的域。我们提出ATLAS，这是一种多源推荐域泛化框架，可从不相交的源域学习共享的、域不变的用户-项目表示，实现对未见域的零样本推荐。ATLAS结合了Gromov-Wasserstein对齐（该对齐保留用户在不同域间的关联方式）、使项目表示在各域间难以区分的对抗目标，以及将用户和项目嵌入压缩到离散潜在空间的残差向量量化（RVQ）码本，在捕捉层级交互模式的同时抑制域特定变异。在五个亚马逊域上训练后直接应用于十个未见域，ATLAS在多数未见域上的表现优于最先进的顺序、基于图、跨域、基于量化及基于LLM的基线模型，HitRate的平均相对提升为24%。消融实验和表示分析验证了各组件的有效性，我们还发现了显著的源域多样性效应：增加源域异质性可大幅提升零样本迁移性能。ATLAS将推荐域泛化确立为零样本推荐的一种有前景的范式。
英文摘要
Recommender systems remain domain-bound: a model trained on one interaction environment typically requires retraining or target-domain adaptation before it can operate on a new catalogue. A recommender trained on movies cannot be directly deployed to recommend groceries or video games. Existing approaches mitigate this by transferring restricted forms of recommendation knowledge, adapting to the target domain, or leveraging large language models (LLMs) for transferable representations. We instead ask whether recommendation-specific knowledge learned solely from multiple heterogeneous domains can generalize to entirely unseen domains without target-domain adaptation or language-model pretraining. We introduce ATLAS, a multi-source recommendation domain generalization framework that learns a shared, domain-invariant user-item representation from disjoint source domains, enabling zero-shot recommendation on unseen domains. ATLAS combines a Gromov-Wasserstein alignment that preserves how users relate to one another across domains, an adversarial objective that makes item representations indistinguishable across domains, and residual vector quantization (RVQ) codebooks that compress user and item embeddings into a discrete latent space, capturing hierarchical interaction patterns while suppressing domain-specific variation. Trained on five Amazon domains and applied directly to ten unseen domains, ATLAS outperforms state-of-the-art sequential, graph-based, cross-domain, quantization-based, and LLM-based baselines on most unseen domains, with an average relative gain in HitRate of 24%. Ablations and representation analyses validate each component, and we identify a pronounced source-domain diversity effect: increasing source heterogeneity substantially improves zero-shot transfer. ATLAS establishes recommendation domain generalization as a promising paradigm for zero-shot recommendation.
Comments18 pages, 5 figures, 14 tables. Includes appendix with proofs and additional experiments
