发表机构
VinUniversity; Griffith University; Aalborg University（VinUniversity; 格里菲斯大学; 奥尔堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对语义ID扩散推荐提出EPIC方法，通过构建个性化候选物品后验分布引导去噪，在四个Amazon基准测试上实现了对强基线的持续性能提升。
AI 中文摘要
语义ID（SID）生成式推荐通过生成离散标记的短元组来预测下一个物品。近期的掩码扩散方法通过双向上下文和灵活解码改进了这一过程，但推荐最终需要在完整的物品目录中进行选择。在每一步去噪过程中，部分SID可能对应多个可行物品，而现有方法主要通过逐位置的标记预测进行推理。我们提出了显式后验物品条件（EPIC），它将显式的物品级竞争引入SID去噪过程。EPIC利用当前生成上下文和用户近期交互，构建了可行候选物品的个性化后验分布，随后将该分布投影回未解决的SID位置，以指导后续的标记决策。预训练的骨干网络保持冻结状态，无需额外的解码器前向传播。在四个Amazon基准测试上的实验表明，EPIC相较于强基线取得了持续的性能提升，而诊断分析显示，这些提升主要源于个性化的转移证据，该证据在去噪过程中保留了有前景的物品假设。
英文摘要
Semantic ID (SID) generative recommendation predicts the next item by generating a short tuple of discrete tokens. Recent masked-diffusion methods improve this process through bidirectional context and flexible decoding, yet recommendation ultimately requires selecting among complete catalog items. At each denoising step, a partial SID can correspond to multiple feasible items, while existing methods primarily reason through position-wise token predictions. We propose Explicit Posterior Item Conditioning (EPIC), which introduces explicit item-level competition into SID denoising. EPIC constructs a personalized posterior over feasible candidate items using the current generation context and the user's recent interactions, then projects this distribution back to unresolved SID positions to guide subsequent token decisions. The pretrained backbone remains frozen and requires no additional decoder forward pass. Experiments on four Amazon benchmarks show consistent improvements over strong baselines, while diagnostic analyses indicate that the gains primarily arise from personalized transition evidence that preserves promising item hypotheses during denoising.
Comments11 pages, 7 figures, 3 tables
