用TransformerVAE实现观测数据到干预分布的快速推断
ACTIVA: Amortized Causal Effect Estimation via Transformer-based Variational Autoencoder
- 基于Transformer的变分自编码器，通过条件隐变量先验实现跨任务知识复用
- 在合成数据和基因表达模拟中显著优于相关基线，减少虚假非后代影响
- 适合需要快速估计多种干预效果的研究者，如生物医学与决策系统
从观测数据预测干预后分布是科学与决策中的核心问题，但受限于因果模糊性、建模假设严格及缺乏任务间知识复用。本文提出ACTIVA，一种基于Transformer的条件变分自编码器，可对观测数据与干预查询进行全干预分布的摊销估计。ACTIVA学习一个条件隐变量先验，支持零样本推理，实现因果知识在多样化训练任务间的迁移。我们给出一致性结果：在理想条件下，其学习目标收敛于与输入观测相容的因果模型所对应的干预分布混合。实证表明，在合成数据集和生物合理的基因表达模拟中，ACTIVA显著优于相关基线，有效降低虚假非后代效应，并达到与强摊销基线相当的性能。结果表明，ACTIVA是一种从观测数据估计干预分布的有前景方法。
原文摘要 · Abstract (English)
Predicting post-intervention distributions from observational data is central to many scientific and decision-making problems, but remains challenging due to causal ambiguity, restrictive modeling assumptions, and the lack of amortization across tasks. We introduce ACTIVA, a transformer-based conditional variational autoencoder for amortized estimation of full interventional distributions from observational data and intervention queries. ACTIVA learns a conditional latent prior that supports zero-shot inference by amortizing causal knowledge across diverse training tasks. We provide a consistency result showing that, under idealized conditions, ACTIVA's learning objective targets a mixture over the interventional distributions of causal models that are observationally compatible with the input. Empirically, on synthetic datasets and biologically realistic gene-expression simulations, ACTIVA substantially outperforms a correlational baseline, reduces spurious non-descendant effects, and achieves competitive performance relative to strong amortized baselines. Our results show that ACTIVA is a promising approach for estimating interventional distributions from observational 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。