AI 中文总结
提出UnpairGR模型，从多类观测中学习统一语义ID空间，在三类基准数据集上验证其可提升完全与不完全观测下的推荐性能。
AI 中文摘要
生成式推荐（Generative Recommendation, GR）将推荐任务建模为对离散语义标识符（IDs）的自回归生成。尽管近期多模态GR方法借助视觉和文本信息优化了语义ID的构建，但它们通常需要物品级别的配对观测数据，这限制了分词仅能在模态可用的交集范围内进行。此外，整合非配对观测数据并非易事，因为微小的表示偏移可能会跨越量化边界，产生不兼容的标识符序列。为应对这一挑战，我们提出了非配对模态无关生成式推荐模型（Unpaired Modality-Agnostic Generative Recommendation, UnpairGR），该模型可从配对观测、仅图像观测和仅文本观测中学习统一的语义ID空间。UnpairGR将模态特定的处理限定为轻量级输入投影，同时在所有观测条件下共享后续的Transformer和残差码本。配对观测建立了可靠性引导的跨模态共识，而单模态观测则直接优化相同的表示和码本。学习到的分词器随后被固定，以作为单一自回归推荐器的稳定目标，无需特征插补、模态特定码本或 fallback 映射。在三个基准数据集上开展的大量实验表明，UnpairGR在完全观测和不完全观测两种设置下均能持续提升推荐性能。
英文摘要
Generative Recommendation (GR) formulates recommendation as autoregressive generation over discrete semantic identifiers (IDs). Although recent multimodal GR methods improve semantic ID construction with visual and textual information, they typically require item-level paired observations, restricting tokenization to the intersection of modality availability. Moreover, incorporating unpaired observations is nontrivial because small representation shifts may cross quantization boundaries and produce incompatible identifier sequences. To address this challenge, we propose \textbf{Unpair}ed Modality-Agnostic \textbf{G}enerative \textbf{R}ecommendation (UnpairGR), which learns a unified semantic-ID space from paired, image-only, and text-only observations. UnpairGR confines modality-specific processing to lightweight input projections while sharing the subsequent Transformer and residual codebooks across all observation conditions. Paired observations establish a reliability-guided cross-modal consensus, whereas unimodal observations directly refine the same representations and codes. The learned tokenizer is then fixed to provide stationary targets for a single autoregressive recommender, without feature imputation, modality-specific codebooks, or fallback mappings. Extensive experiments on three benchmark datasets demonstrate that UnpairGR consistently improves recommendation performance under both fully observed and incomplete-observation settings.
