[论文] Mutable Low-Rank Sketches for Retrain-Free Recommendation

论文概要

研究领域: ML
作者: Hector J. Garcia, Nick Clayton
发布时间: 2025-07-16
arXiv: 2507.12497

中文摘要

两阶段推荐系统的一个常见瓶颈是嵌入向量陈旧：当用户对新品评分时，其嵌入向量在下一次重训练周期前保持不变。本文提出可变草图（mutable sketches），将每位用户的偏好存储在 KP-tree（一种带求和聚合的稀疏线段树）中，一次性拟合低秩投影，并在评分到达时即时重新计算嵌入。我们证明每个新观测单调收紧预测误差包络（定理1），这是 FunkSVD 和 eALS 所不具备的保证。在 KuaiRec 数据集上，可变草图仅使用1.8%数据即达到0.810的RMSE，而 ALS 使用100%数据为0.822，每批次更新速度快8倍。新用户在首次评分后不到1毫秒即可获得个性化推荐，无需模型重训练。跨密度区间的采样策略比较表明，KP-tree 的范数比例采样在稀疏数据（低于1%密度）上提供40-130%更优的物品覆盖，而稠密矩阵上均匀采样已足够。

原文摘要

A common bottleneck in two-stage recommendation is embedding staleness: when a user rates a new item, their embedding remains fixed until the next retrain cycle. We propose mutable sketches, which store each user's preferences in a KP-tree (a sparse segment tree with sum aggregation), fit a low-rank projection once, and recompute embeddings on-the-fly as ratings arrive. We prove that each new observation monotonically tightens the prediction error envelope (Theorem 1), a guarantee that FunkSVD and eALS lack. On KuaiRec, the mutable sketch achieves 0.810 RMSE at 1.8% data read vs. ALS 0.822 at 100%, with 8x faster per-batch updates. A new user receives personalized recommendations in less than 1 ms after their first rating, with no model retraining required. A comparison of sampling strategies across density regimes shows that the KP-tree's norm-proportional sampling provides 40-130% bett...

自动采集于 2026-07-19

#论文 #arXiv #ML #小凯