arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.01766cs.LG
收藏

学习因果对齐以实现可靠的疾病诊断

Learning Causal Alignment for Reliable Disease Diagnosis

School of Computer Science, Peking University(北京大学计算机学院);School of Data Science, Fudan University(复旦大学数据科学学院);Computer Science Department, Shanghai Jiao Tong University(上海交通大学计算机科学系);Center on Frontiers of Computing Studies, Peking University(北京大学计算前沿研究中心);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Nat’l Eng. Research Center of Visual Technology, Peking University(北京大学视觉技术国家工程研究中心);State Key Lab. of General Artificial Intelligence, Peking University(北京大学通用人工智能国家重点实验室)

Mingzhou Liu, Ching-Wen Lee, Xinwei Sun, Yu Qiao, Yizhou Wang

AI总结:

本文提出基于因果关系的对齐框架,通过反事实生成识别模型决策因果链,并设计因果对齐损失使模型关注与专家一致的因果因素,从而提升医学诊断的可靠性。

摘要:

将机器学习算法的决策过程与经验丰富的放射科医生的决策过程对齐,对于可靠诊断至关重要。尽管现有方法试图将算法的诊断行为与训练数据中反映的放射科医生行为对齐,但这种对齐主要是关联性的而非因果性的,导致产生可能无法良好迁移的伪相关。在本文中,我们提出了一种基于因果关系的对齐框架,旨在将模型的决策过程与专家的决策过程对齐。具体而言,我们首先采用反事实生成来识别模型决策的因果链。为了使该因果链与专家的因果链对齐,我们提出了一种因果对齐损失,强制模型关注整个因果链中每个决策步骤背后的因果因素。为了优化这一将反事实生成器作为模型参数隐函数包含在内的损失,我们利用隐函数定理并结合共轭梯度法进行高效估计。我们在两个医学诊断应用上验证了所提方法的有效性,展示了对放射科医生的忠实对齐。

英文摘要:

Aligning the decision-making process of machine learning algorithms with that of experienced radiologists is crucial for reliable diagnosis. While existing methods have attempted to align their diagnosis behaviors to those of radiologists reflected in the training data, this alignment is primarily associational rather than causal, resulting in pseudo-correlations that may not transfer well. In this paper, we propose a causality-based alignment framework towards aligning the model's decision process with that of experts. Specifically, we first employ counterfactual generation to identify the causal chain of model decisions. To align this causal chain with that of experts, we propose a causal alignment loss that enforces the model to focus on causal factors underlying each decision step in the whole causal chain. To optimize this loss that involves the counterfactual generator as an implicit function of the model's parameters, we employ the implicit function theorem equipped with the conjugate gradient method for efficient estimation. We demonstrate the effectiveness of our method on two medical diagnosis applications, showcasing faithful alignment to radiologists.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑