Generative recommendation (GR) typically first quantizes continuous item embeddings into multi-level semantic IDs (SIDs), and then generates the next item via autoregressive decoding. Although existing methods are already competitive in terms of recommendation performance, directly inheriting the autoregressive decoding paradigm from language models still suffers from three key limitations: (1) autoregressive decoding struggles to jointly capture global dependencies among the multi-dimensional features associated with different positions of SID; (2) using a unified, fixed decoding path for the same item implicitly assumes that all users attend to item attributes in the same order; (3) autoregressive decoding is inefficient at inference time and struggles to meet real-time requirements. To tackle these challenges, we propose MDGR, a Masked Diffusion Generative Recommendation framework that reshapes the GR pipeline from three perspectives: codebook, training, and inference. (1) We adopt a parallel codebook to provide a structural foundation for diffusion-based GR. (2) During training, we adaptively construct masking supervision signals along both the temporal and sample dimensions. (3) During inference, we develop a warm-up-based two-stage parallel decoding strategy for efficient generation of SIDs. Extensive experiments on multiple public and industrial-scale datasets show that MDGR outperforms ten state-of-the-art baselines by up to 10.78%. Furthermore, by deploying MDGR on a large-scale online advertising platform, we achieve a 1.20% increase in revenue, demonstrating its practical value. The code will be released upon acceptance.

翻译：生成式推荐（GR）通常首先将连续物品嵌入量化为多层级语义ID（SID），然后通过自回归解码生成下一个物品。尽管现有方法在推荐性能方面已具有竞争力，但直接沿用语言模型的自回归解码范式仍存在三个关键局限：（1）自回归解码难以联合捕捉SID不同位置关联的多维特征之间的全局依赖关系；（2）对同一物品使用统一、固定的解码路径，隐含假设所有用户都以相同顺序关注物品属性；（3）自回归解码在推理时效率低下，难以满足实时性要求。为应对这些挑战，我们提出MDGR——一个掩码扩散生成式推荐框架，从三个维度重塑GR流程：码本、训练与推理。（1）我们采用并行码本，为基于扩散的GR提供结构化基础。（2）在训练阶段，我们沿时间和样本维度自适应地构建掩码监督信号。（3）在推理阶段，我们开发了一种基于预热的两阶段并行解码策略，以实现SID的高效生成。在多个公开及工业级数据集上的大量实验表明，MDGR优于十种最先进的基线方法，性能提升最高达10.78%。此外，通过将MDGR部署于大规模在线广告平台，我们实现了1.20%的收入增长，证明了其实际应用价值。代码将在论文录用后开源。