通过分解深度双网络的不确定性，定位模型出错根源。
Localising Dropout Variance in Twin Networks
- 独立开关共享编码器与输出头的蒙特卡洛丢弃，分解预测方差。
- 编码器方差主导分布外样本的误差，真实数据中占比达89%。
- 适合需要诊断模型缺陷、决定数据收集方向的研究者。
准确的个体治疗效应估计不仅需要可靠的点预测，还需能帮助从业者定位模型失败来源的不确定性度量。本文为深度双网络模型提出逐层方差分解方法：通过独立地在共享编码器和结果头中开启蒙特卡洛丢弃，将总预测方差拆分为编码器分量（σ_{ enc}^2）和头分量（σ_{ head}^2），满足σ_{ enc}^2 + σ_{ head}^2 ≈ σ_{ tot}^2。在三种合成协变量偏移场景下，分布外情况下编码器分量主导（ρ_{ enc}=0.53），而仅当编码器不确定性被控制后，头分量才具有信息量。在一个包含多变量偏移的真实双胞胎队列上，仅编码器方差在分布外样本上显著上升，成为主要误差预测因子（ρ_{ enc}≈0.89），而头方差保持平稳。该分解方法对标准蒙特卡洛丢弃开销几乎无增益，可有效指导是否需采集更多多样协变量或更多结果数据。
原文摘要 · Abstract (English)
Accurate individual treatment-effect estimation demands not only reliable point predictions but also uncertainty measures that help practitioners \emph{locate} the source of model failure. We introduce a layer-wise variance decomposition for deep twin-network models: by toggling Monte Carlo Dropout independently in the shared encoder and the outcome heads, we split total predictive variance into an \emph{encoder component} ($σ_{\mathrm{enc}}^2$) and a \emph{head component} ($σ_{\mathrm{head}}^2$), with $σ_{\mathrm{enc}}^2 + σ_{\mathrm{head}}^2 \approx σ_{\mathrm{tot}}^2$ by the law of total variance. Across three synthetic covariate-shift regimes, the encoder component dominates under distributional shift ($ρ_{\mathrm{enc}}=0.53$) while the head component becomes informative only once encoder uncertainty is controlled. On a real-world twins cohort with induced multivariate shift, only $σ_{\mathrm{enc}}^2$ spikes on out-of-distribution samples and becomes the primary error predictor ($ρ_{\mathrm{enc}}\!\approx\!0.89$), while $σ_{\mathrm{head}}^2$ remains flat. The decomposition adds negligible cost over standard MC Dropout and provides a practical diagnostic for deciding whether to collect more diverse covariates or more outcome data.
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。