arXiv:2510.25005cs.AIcs.LG2025-10NeurIPS
研究带循环依赖的因果模型在软干预下的反事实推理方法
Cyclic Counterfactuals under Shift-Scale Interventions
- 提出在循环因果模型中处理平移与缩放干预的新框架
- 首次实现对含反馈回路系统的反事实推断
- 适合从事因果推断与动态系统建模的研究者
大多数反事实推理框架传统上假设结构因果模型（SCM）是无环的，即有向无环图（DAG）。然而，许多现实系统（如生物系统）包含反馈回路或循环依赖，违反了无环性。本文研究在循环结构因果模型下，针对平移-缩放干预（即软性、政策风格的变量机制调整）的反事实推理问题。
原文摘要 · Abstract (English)
Most counterfactual inference frameworks traditionally assume acyclic structural causal models (SCMs), i.e. directed acyclic graphs (DAGs). However, many real-world systems (e.g. biological systems) contain feedback loops or cyclic dependencies that violate acyclicity. In this work, we study counterfactual inference in cyclic SCMs under shift-scale interventions, i.e., soft, policy-style changes that rescale and/or shift a variable's mechanism.
因果推断循环模型反事实
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。