Lattice通过置信度门控激活行为原型，提升序列预测准确性。
Lattice: A Confidence-Gated Hybrid System for Uncertainty-Aware Sequential Prediction with Behavioral Archetypes
- 用二值置信度门控决定是否启用行为原型进行评分。
- 在MovieLens上，门控模式下相比基线提升HR@10达+31.7%。
- 适用于需要可解释性与不确定性感知的推荐系统场景。
我们提出Lattice，一种混合序列预测系统，通过二值置信度门控条件性激活学习到的行为结构。系统将行为窗口归纳为行为原型，并仅在支持性置信信号超过验证校准阈值时启用原型评分，不确定时回退至主干模型预测。主要评估指标是将Lattice加入固定主干对相同测试样本的控制效应。在MovieLens（30组配对种子，全目录排序）上，LSTM+Lattice在门控模式下相较LSTM主干提升HR@10达+31.7%（p远小于10^-20）；非门控融合达+58.7%。我们不主张门控能最大化总体准确率。使用主干原生原型（在各主干嵌入空间中拟合），门控提升分别为+13.3%（Transformer）和+17.0%（SASRec），评估设计一致。早期版本中约0%的Transformer行反映无效跨主干迁移，不代表组合无法提升强编码器。Amazon Electronics提供跨领域支持证据（门控提升+124.0%，15个种子，高方差）。附录中的控制转移检验显示门控在分布偏移下拒绝激活。独立的SASRec和BERT4Rec得分仅为上下文参考，非目标估计量。我们报告组合的效果及其激活条件；生产校准与实现细节因专利审查仍属保密。
原文摘要 · Abstract (English)
We introduce Lattice, a hybrid sequential prediction system that conditionally activates learned behavioral structure using binary confidence gating. The system summarizes behavior windows as behavioral archetypes and activates archetype-based scoring only when an in-support confidence signal exceeds a validation-calibrated threshold, falling back to backbone predictions when uncertain. Our primary estimand is the controlled effect of adding Lattice to a fixed backbone on identical test rows. On MovieLens (30 paired seeds, full-catalog ranking), LSTM+Lattice improves HR@10 by +31.7% (gated) versus the LSTM backbone alone (p much less than 10^-20); ungated fusion reaches +58.7% on the same protocol. We do not claim gating maximizes pooled accuracy. With backbone-native archetypes (fit in each backbone's embedding space), gated lifts of +13.3% (transformer) and +17.0% (SASRec) hold under the same evaluation design. A prior approximately 0% transformer row in version 1 reflected an invalid cross-backbone transfer, not evidence that composition cannot help stronger encoders. Amazon Electronics provides supporting cross-domain evidence (+124.0% gated, 15 seeds, high variance). Controlled shift checks (appendix) illustrate gate refusal under distribution shift. Standalone SASRec and BERT4Rec scores are contextual references, not the target estimand. We report what composition achieves and when it activates; production calibration and implementation details remain proprietary pending patent prosecution.
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。