用反事实推理消除语音抑郁检测中的性别偏见，提升公平性与准确率。
Mitigating Gender Bias in Depression Detection via Counterfactual Inference
- 基于因果图建模，将性别偏见识别为性别对预测的直接因果效应。
- 在DAIC-WOZ数据集上，性别偏差降低且整体检测性能提升。
- 适用于需高公平性的医疗语音诊断系统，尤其关注性别敏感场景。
基于语音的抑郁检测模型表现优异，但常因训练数据不平衡而存在性别偏见。流行病学数据显示女性抑郁发病率更高，导致模型学习到性别与抑郁之间的虚假关联，从而过度诊断女性患者，对男性患者表现较差，引发严重的公平性问题。为此，我们提出一种基于因果推断的新型反事实去偏框架。构建因果图以建模决策过程，将性别偏见识别为性别对预测结果的直接因果效应。推理阶段，采用反事实推理估计并剔除该直接效应，使模型主要依赖真实的声学病理特征。在使用两个先进声学骨干网络的DAIC-WOZ数据集上进行的大量实验表明，该框架不仅显著降低性别偏见，还优于现有去偏策略，提升了整体检测性能。
原文摘要 · Abstract (English)
Audio-based depression detection models have demonstrated promising performance but often suffer from gender bias due to imbalanced training data. Epidemiological statistics show a higher prevalence of depression in females, leading models to learn spurious correlations between gender and depression. Consequently, models tend to over-diagnose female patients while underperforming on male patients, raising significant fairness concerns. To address this, we propose a novel Counterfactual Debiasing Framework grounded in causal inference. We construct a causal graph to model the decision-making process and identify gender bias as the direct causal effect of gender on the prediction. During inference, we employ counterfactual inference to estimate and subtract this direct effect, ensuring the model relies primarily on authentic acoustic pathological features. Extensive experiments on the DAIC-WOZ dataset using two advanced acoustic backbones demonstrate that our framework not only significantly reduces gender bias but also improves overall detection performance compared to existing debiasing strategies.
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。