用因果模型消除多类图像分类中的性别偏见。
Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling
- 构建每个情绪类别的因果模型，调整预测概率以减轻偏见。
- 女性被误判为'开心'或'难过'的倾向显著降低。
- 提升公平性同时保持甚至略微提高准确率，适合关注算法公正的研究者。
本研究提出一种基于因果建模的方法，用于检测并缓解多类别分类中的算法偏见。数据集源自FairFace，并通过预训练的DeepFace模型补充情感标签。自研卷积神经网络（CNN）包含四个卷积块，后接全连接层和丢弃层以防止过拟合。分析发现，该模型存在性别偏见：女性更易被分类为'开心'或'难过'，男性则更易被归为'中性'。为此，采用一对一（OvA）策略，为每个情绪类别构建因果模型，对CNN的预测概率进行校正。最终通过选择最高概率类别整合调整后的结果。去偏后的分类在所有类别上均实现更好的性别公平性，且对整体准确率影响极小，甚至略有提升。研究证明算法公平性与准确性并非必然冲突。所有数据与代码均已公开可下载。
原文摘要 · Abstract (English)
This study describes a procedure for applying causal modeling to detect and mitigate algorithmic bias in a multiclass classification problem. The dataset was derived from the FairFace dataset, supplemented with emotional labels generated by the DeepFace pre-trained model. A custom Convolutional Neural Network (CNN) was developed, consisting of four convolutional blocks, followed by fully connected layers and dropout layers to mitigate overfitting. Gender bias was identified in the CNN model's classifications: Females were more likely to be classified as "happy" or "sad," while males were more likely to be classified as "neutral." To address this, the one-vs-all (OvA) technique was applied. A causal model was constructed for each emotion class to adjust the CNN model's predicted class probabilities. The adjusted probabilities for the various classes were then aggregated by selecting the class with the highest probability. The resulting debiased classifications demonstrated enhanced gender fairness across all classes, with negligible impact--or even a slight improvement--on overall accuracy. This study highlights that algorithmic fairness and accuracy are not necessarily trade-offs. All data and code for this study are publicly available for download.
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。