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:摘要直接研究因果发现中的可识别结构、马尔可夫等价类与架构偏差,属于因果推断,图预测不等同网络干扰研究。

反馈分类问题

Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal Learning

学习可识别结构以避免深度神经网络监督因果学习的偏差

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
Jiaru Zhang
Rui Ding
Qiang Fu
Bojun Huang
Zizhen Deng
Yang Hua
Haibing Guan
Shi Han
Dongmei Zhang

学习可识别结构以避免深度神经网络监督因果学习的偏差

研究问题
监督因果学习中先编码节点、再独立预测有向边的神经网络架构,是否存在不可消除的偏差,学习何种结构能够避免它?
方法与思路
作者提出 SiCL,预测骨架矩阵与表示 v 结构的三阶张量,并配置带单向注意力的成对编码器,学习节点对的内外关系。
材料陈述的贡献
摘要称节点—边架构存在系统偏差,而基于马尔可夫等价类中可识别结构的 SiCL 可避免该偏差,并报告基准比较优势。
阅读关注点
应核对系统偏差结论针对的架构范围、标准等价类设定的假设,以及可识别预测目标如何支持一致的因果发现估计。
阅读边界
这是 arXiv 预印本摘要,不能据此认定同行评审或期刊接收;摘要未说明完整理论条件,骨架与 v 结构不保证唯一识别全部方向。

原文摘要

Causal discovery is a structured prediction task that aims to predict causal relations among variables based on their data samples. Supervised Causal Learning (SCL) is an emerging paradigm in this field. Existing Deep Neural Network (DNN)-based methods commonly adopt the "Node-Edge approach", in which the model first computes an embedding vector for each variable-node, then uses these variable-wise representations to concurrently and independently predict for each directed causal-edge. In this paper, we first show that this architecture has some systematic bias that cannot be mitigated regardless of model size and data size. We then propose SiCL, a DNN-based SCL method that predicts a skeleton matrix together with a v-tensor (a third-order tensor representing the v-structures). According to the Markov Equivalence Class (MEC) theory, both the skeleton and the v-structures are identifiable causal structures under the canonical MEC setting, so predictions about skeleton and v-structures do not suffer from the identifiability limit in causal discovery, thus SiCL can avoid the systematic bias in Node-Edge architecture, and enable consistent estimators for causal discovery. Moreover, SiCL is also equipped with a specially designed pairwise encoder module with a unidirectional attention layer to model both internal and external relationships of pairs of nodes. Experimental results on both synthetic and real-world benchmarks show that SiCL significantly outperforms other DNN-based SCL approaches.

笔记与分组