发表机构
Duke University; Meta（杜克大学; Meta）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长历史序列推荐中缓存记忆不均匀保留多尺度语义的问题，提出多分辨率自适应路由模型MARS，利用多半衰期循环轨道与稀疏路由读取器提升推荐效果，在三个数据集上超越基线。
AI 中文摘要
长历史推荐器通常将每个用户的历史压缩成一个紧凑的、与候选无关的存储器，该存储器被缓存并复用以对大型候选池进行评分。我们表明，真实用户历史展现出多尺度的语义结构，短期意图、中期兴趣和长期偏好共存于一个序列中，而整体式缓存存储器对这些尺度的保留是不均匀的：线性探针恢复近期和中期内容的效果远差于长期内容。我们将这种失效模式称为\u201c时间混叠\u201d。我们提出MARS，一种多分辨率用户存储器，它将完整历史写入锚定在不同半衰期的循环状态轨道中，以及一个稀疏路由读取器，通过为每个种子选择相关的时间分辨率来物化紧凑的种子存储器，从而保持固定大小的候选评分。MARS在三个公开数据集上优于强基线，且其增益随历史长度增长而增加。通过配对检验的组件匹配消融实验表明，时间多样性和选择性路由各自带来的贡献超出了硬窗口存储器或增加容量所能提供的。在用户内部行为转变之后，MARS相对于其接口匹配基线的优势也会扩大，其服务每个用户1000个候选的延迟约为该基线热缓存服务延迟的1.02倍。
英文摘要
Long-history recommenders often compress each user's history into a compact, candidate-independent memory that is cached and reused to score large candidate pools. We show that real user histories exhibit multi-scale semantic structure, with short-lived intent, medium-term interests, and long-term preferences coexisting in one sequence, and that monolithic cached memories preserve these scales unevenly: linear probes recover recent and mid-range content far worse than long-range content. We call this failure mode \textit{temporal aliasing}. We propose \textbf{MARS}, a multi-resolution user memory that writes the full history into recurrent state tracks anchored to different half-lives, and a sparse routing reader that materializes compact seed memories by selecting the relevant temporal resolutions for each seed, preserving fixed-size candidate scoring. MARS outperforms strong baselines on three public datasets, with gains that grow with history length. Component-matched ablations with paired tests show that temporal diversity and selective routing each contribute beyond what hard-window memories or added capacity provide. The advantage of MARS over its interface-matched baseline also widens after within-user behavioral shifts, at about $1.02\times$ that baseline's warm-cache serving latency for $1{,}000$ candidates per user.
