剔除目标域数据可显著提升物理模型外推性能
Excluding the Target Domain Improves Extrapolation: Deconfounded Hierarchical Physics Constraints
- 引入去混淆分层门控机制，动态识别并消除温度干扰
- 预训练时排除目标域数据，外推误差降低39%
- 适用于电池温度等跨域物理建模场景
物理约束深度生成模型在分布外条件下的外推能力仍面临挑战。现有方法将物理约束作为单一静态正则项均匀施加于生成过程，未考虑物理定律的层级结构及混杂变量问题。本文提出去混淆分层门控（DHG）机制，通过反事实估计与后门调整消除温度混杂影响，使分层约束反映真实的物理不一致性。实验发现：预训练时排除目标域数据，外推性能提升39%（RMSE 0.224 vs. 0.324）。这是因为FNO能学习更具泛化性的领域无关物理模式。在锂离子电池温度外推基准测试中（训练于24℃，评估范围4.0–43.0℃），本方法达RMSE=0.215，较无约束基线（Pure CFM: 0.397）提升46%。
原文摘要 · Abstract (English)
Extrapolation to out-of-distribution conditions is a fundamental challenge for physics-constrained deep generative models. Existing methods apply physical constraints as a single static regularization term uniformly across the generation process, and address neither the hierarchical structure of physical laws and the confounding variable problem. We propose the Deconfounded Hierarchical Gate (DHG), which serves as a diagnostic and control mechanism: it identifies when and how strongly temperature confounding contaminates each constraint level, so that hierarchical gates reflect intrinsic physical inconsistency rather than spurious temperature effects. DHG combines counterfactual estimation via the do-operator with backdoor adjustment to remove confounding, then applies Coarse-to-Fine physical constraints progressively. We report a counter-intuitive finding in pretraining: excluding the target-domain data from pretraining outperforms including it by 39% in extrapolation performance (RMSE 0.224 vs. 0.324). This occurs because FNO learns domain-agnostic physical patterns that transfer more effectively when the target domain is withheld. On a lithium-ion battery temperature extrapolation benchmark (trained at 24 degrees Celsius, evaluated at 4.0--43.0 degrees Celsius), our method achieves RMSE = 0.215, a 46% improvement over the unconstrained baseline (Pure CFM: 0.397).
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。