跳到正文
← 返回论文列表与筛选
阅读说明

本页整理公开书目信息,不生成学术质量评分。AI 解读根据题名及所注明的摘要或原文片段生成,未完成全文核验,可能有误;具体假设、证明与结论请核对原文。摘要保留来源文本,未经模型改写。

DOI 首次登记不等于接收或发表日期。部分更正、评论等条目没有独立摘要;缺少可靠材料时保留待补状态。

本页为预印本版本;arXiv 收录、作者填写的期刊信息以及作者既有发表经历,都不单独证明本篇已接收。作者发表记录按 OpenAlex 身份与完整姓名、本站覆盖期刊 ISSN 及正式卷期核对,只展示已核实例,档案仍可能误合并。

引用量采用 OpenAlex 单条关联记录,不合计多个记录;关联记录可能包含正式发表版本,不等于此版本单独引用。缺失不视为零,引用指标不代表论文质量。

关注作者按书目中的完整姓名匹配,同名和姓名变体需人工辨别。相关论文先按共享细分方向和具体方法排列,再参考通用方法与发表日期。

分类依据与纠错

AI 根据所提供的论文材料归类:摘要直接研究存在潜在混杂时高维因果查询的识别与生成式求解。

反馈分类问题

正在核对关联版本…

代码、数据与补充材料

正在核对对应版本的资源…

关注这篇论文的作者
Md Musfiqur Rahman
Murat Kocaoglu

面向高维因果推断的深度因果生成模型模块化学习

研究问题
在图像等高维变量与潜在混杂并存时,如何利用已知因果结构和预训练生成模型,高效回答可识别的因果查询?
方法与思路
作者提出 Modular-DCM,以模块化对抗训练学习深度因果生成模型,并复用预训练条件生成模块来产生查询样本。
材料陈述的贡献
摘要称,方法可证明地从可识别因果查询中采样,并通过图像数据实验展示基准比较、训练收敛及因果不变预测用途。
阅读关注点
应核对已知因果结构与潜在混杂的表示方式、模块复用所需兼容条件,以及理论采样保证如何对应有限训练误差。
阅读边界
这是 arXiv 预印本,不能据此认定已同行评审或获期刊接收;摘要未列出证明条件,有限训练后的查询准确性也未量化。

原文摘要

Sound and complete algorithms have been proposed to compute identifiable causal queries using the causal structure and data. However, most of these algorithms assume accurate estimation of the data distribution, which is impractical for high-dimensional variables such as images. On the other hand, modern deep generative architectures can be trained to sample from high-dimensional distributions. However, training these networks are typically very costly. Thus, it is desirable to leverage pre-trained models to answer causal queries using such high-dimensional data. To address this, we propose modular training of deep causal generative models that not only makes learning more efficient, but also allows us to utilize large, pre-trained conditional generative models. To the best of our knowledge, our algorithm, Modular-DCM is the first algorithm that, given the causal structure, uses adversarial training to learn the network weights, and can make use of pre-trained models to provably sample from any identifiable causal query in the presence of latent confounders. With extensive experiments on the Colored-MNIST dataset, we demonstrate that our algorithm outperforms the baselines. We also show our algorithm's convergence on the COVIDx dataset and its utility with a causal invariant prediction problem on CelebA-HQ.

笔记与分组
相关领域论文