发表机构
Independent Researcher Vancouver Canada; Independent Researcher（; ）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出MEMOIR框架用于推荐，将用户交互历史按时间窗口分割，用语言模型生成记忆并聚合为用户表示。在亚马逊评论数据上实验，与UniSRec对比，发现其在不同偏好漂移程度用户中有不同表现，此漂移分层模式是主要贡献。
AI 中文摘要
我们提出了MEMOIR框架，它将用户交互历史分割成时间窗口，使用语言模型为每个时期生成语义行为记忆，并将当前状态、演变方向和预测未来聚合为单个用户表示。在亚马逊2023年评论的电子产品和服装鞋履珠宝类别上，MEMOIR在聚合NDCG@10上与最强基线UniSRec在统计上相当（0.0643对0.0641），在四个报告指标上2-2平分：MEMOIR在NDCG@10和MRR上领先，UniSRec在HR@10和HR@20上领先。消融研究发现，没有单个架构组件能单独解释MEMOIR相对于基于ID的SASRec约18%的相对增益。按综合偏好漂移分数分层测试性能揭示了增益集中的地方：MEMOIR在分布的高漂移和低漂移极端用户中的排名质量指标（NDCG@10，MRR）上领先，而UniSRec在所有漂移层的面向数量的HR@10/HR@20指标上领先，并在中间带的排名质量上略胜MEMOIR。我们将这种漂移分层模式报告为MEMOIR最实质性和可重复的发现，并提出其成立原因作为未来工作的开放问题。
英文摘要
We propose MEMOIR, a framework that segments user interaction histories into temporal windows, generates semantic behavioral memory for each period using an LLM, and aggregates current state, evolution direction, and predicted future into a single user representation. On the Electronics and Clothing_Shoes_and_Jewelry categories of Amazon Reviews 2023, MEMOIR is statistically tied with UniSRec, the strongest baseline, on aggregate NDCG@10 (0.0643 vs. 0.0641), splitting the four reported metrics 2-2: MEMOIR leads NDCG@10 and MRR, UniSRec leads HR@10 and HR@20. An ablation study finds that no single architectural component - the evolution-preserving contrastive loss, its directional-consistency term, or temporal window segmentation itself - individually explains much of MEMOIR's approximately 18% relative gain over ID-based SASRec; all four ablations land within 2% of the full model on aggregate NDCG@10. Stratifying test performance by a composite preference-drift score instead reveals where the gain concentrates: MEMOIR leads on ranking-quality metrics (NDCG@10, MRR) specifically among users at the high- and low-drift extremes of the distribution, while UniSRec leads the volume-oriented HR@10/HR@20 metrics across all drift strata and edges out MEMOIR on ranking quality in the middle band. We report this drift-stratified pattern, rather than the near-tied aggregate numbers or any single ablated component, as MEMOIR's most substantive and reproducible finding, and surface why it holds as an open question for future work.
Comments6 pages, 2 figures
