发表机构
Jilin University; City University of Hong Kong（吉林大学; 香港城市大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对序列推荐中项目目录离散稀疏致欧几里得路径失效问题，提出MIRAGE框架，利用项目共现图校正嵌入几何，使插值路径状态与局部锚点对齐，保留原始概率路径仅训练用图，实验表明其性能优于基线。
AI 中文摘要
传统推荐器通过优化观察到的用户-项目关系来捕捉用户偏好，而连续生成式推荐还学习合成目标项目的轨迹。流匹配通过在连续嵌入空间中通过中间状态将初始噪声逐渐塑造成确定的下一个项目表示来驱动这个过程。然而，项目目录是离散且稀疏支持的，这意味着即使是直接的欧几里得路径也可能穿过几乎没有有效项目语义证据的连续区域。我们将这种失败形式化为欧几里得空洞，提出了MIRAGE，一种用于序列推荐中加速嵌入生成的流形感知校正框架，它围绕不变的直接概率路径校正学习到的嵌入几何。通过利用项目共现图作为潜在语义流形的代理，MIRAGE将插值路径状态与局部锚点对齐，重新组织嵌入空间以在有效项目支持中确定轨迹。MIRAGE保留原始概率路径并仅在训练期间使用图，从而实现准确高效的一步推理。在四个真实世界数据集上的广泛实验表明，MIRAGE始终优于现有基线，有效提高对稀疏观察目标的性能，同时实现稳健的整体准确性。我们的代码将在发表后公开。
英文摘要
Conventional recommenders capture users' preferences by optimizing observed user-item relations, whereas continuous generative recommendation additionally learns the trajectory of synthesizing a target item. Flow matching drives this process by gradually shaping initial noise into a definitive next-item representation through intermediate states in a continuous embedding space. However, item catalogs are discrete and sparsely supported, meaning even a straight Euclidean path can cross continuous regions that contain little evidence of valid item semantics. Formalizing this failure as the Euclidean void, we propose MIRAGE, a Manifold-Informed Rectification framework for Accelerated Generation of Embeddings in sequential recommendation, which rectifies the learned embedding geometry around an unchanged straight probability path. By leveraging an item co-occurrence graph as a proxy for the underlying semantic manifold, MIRAGE aligns interpolated path states with local anchors, reorganizing the embedding space to ground the trajectory in valid item support. MIRAGE retains the original probability path and uses the graph only during training, thereby enabling accurate and efficient one-step inference. Extensive experiments on four real-world datasets reveal that MIRAGE consistently outperforms state-of-the-art baselines, effectively boosting performance on sparsely observed targets while achieving robust overall accuracy. Our code will be made publicly available upon publication.
