No evaluation without fair representation : Impact of label and selection bias on the evaluation, performance and mitigation of classification models
该论文通过引入可控偏差的评估框架,实证分析了标签偏差和选择偏差对分类模型评估、性能及去偏方法有效性的差异化影响,揭示了在无偏测试集下公平性与准确性之间不存在权衡,并强调了针对特定偏差类型优化评估与缓解策略的重要性。