区分预测与记忆,用双时间尺度控制用户画像更新
Prediction Is Not Memory: Dual-Timescale Gated Profile Writing for Persistent User Modeling
- 提出近/远期双时序协议,区分短期行为与长期偏好
- 在MicroLens-100K上将远期画像偏差降低至14.5%,覆盖率达77%
- 适合需要长期稳定用户建模的推荐系统开发者
持久化用户画像在推荐系统中日益作为可复用的记忆存在,但常见更新机制混淆了两个决策:预测交互行为与决定该行为是否应持久记录。观察到的行为若反映临时情境、探索或短期满足,而非稳定偏好,则强行写入画像可能有害。本文提出选择性写入控制机制:在交互发生后,判断是否及以多强程度写入持久画像。设计近-远期离线协议,近期证据提供弱写入风险监督,远期证据用于评估。引入SPW-Gate轻量级写入风险门控器,利用长期、短期和候选画像漂移特征。在MicroLens-100K数据集上,全量写入导致远期画像对齐失败率达22.45%;而SPW-Gate将此降低至约14.5%,同时保持约77%的写入覆盖率。对比实验表明,提升非单纯因写入减少所致,且下一项预测置信度不足以替代持久写入有效性判断。
原文摘要 · Abstract (English)
Persistent user profiles increasingly serve as reusable memory in recommender systems, but common update pipelines conflate two decisions: predicting an interaction and deciding whether it should persist in the profile. After an interaction is observed, many systems treat it as evidence for updating durable user state. This assumption can be harmful when the event reflects transient context, exploration, exposure, or short-term satisfaction rather than stable preference formation. We formulate this boundary as selective profile-write control: after an observed interaction, a system should decide whether, and how strongly, to write it into the persistent profile. We introduce a chronological near/far offline protocol in which near-future evidence provides weak write-risk supervision and far-future evidence is reserved for evaluation. We instantiate the controller as SPW-Gate, a lightweight write-risk gate using long-term, short-term, and candidate-profile drift features. On MicroLens-100K, write-all updating hurts far-future profile alignment in 22.45% of test cases under the main protocol. SPW-Gate reduces far hurt to about 14.5% while preserving about 77% write coverage. Matched-coverage controls and prediction-confidence baselines show that the gain is not merely a by-product of writing less, and that next-item confidence is not a sufficient proxy for persistent write validity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。