通过对抗学习提升年龄预测模型的泛化与公平性
Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications
- 采用对抗表示学习构建对种族、性别等属性不变的特征
- 在小鼠转录组数据上实现稳定预测，与已有研究结果一致
- 模型兼具可解释性，适合需公平性与因果推断的研究者
时序年龄预测模型常因种族、性别或组织等外生属性导致分布外（OOD）泛化失败。为提升泛化能力并避免结果过度乐观，需学习对这些属性不变的表示。在预测场景中，该属性驱动偏见缓解；在因果分析中，它们是混杂因子；保护这些属性则有助于实现公平。本文以理论严谨的方式系统探讨这些概念，提出基于对抗表示学习的可解释神经网络模型。利用公开的小鼠转录组数据集，对比传统机器学习模型，验证该模型在预测上的稳定性。结果显示，其预测结果与一项已发表研究中关于艾拉米普瑞蒂德对小鼠骨骼肌和心肌影响的结果一致。最后讨论了从纯预测模型中推导因果解释的局限性。
原文摘要 · Abstract (English)
Chronological age predictors often fail to achieve out-of-distribution (OOD) gen- eralization due to exogenous attributes such as race, gender, or tissue. Learning an invariant representation with respect to those attributes is therefore essential to improve OOD generalization and prevent overly optimistic results. In predic- tive settings, these attributes motivate bias mitigation; in causal analyses, they appear as confounders; and when protected, their suppression leads to fairness. We coherently explore these concepts with theoretical rigor and discuss the scope of an interpretable neural network model based on adversarial representation learning. Using publicly available mouse transcriptomic datasets, we illustrate the behavior of this model relative to conventional machine learning models. We observe that the outcome of this model is consistent with the predictive results of a published study demonstrating the effects of Elamipretide on mouse skeletal and cardiac muscle. We conclude by discussing the limitations of deriving causal interpretation from such purely predictive models.
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。