论文标题
通过公平干预措施打破有条件产生的虚假因果关系
Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling
论文作者
论文摘要
为了捕获样品和标签之间的关系，有条件的生成模型通常从训练数据集继承了虚假的相关性。这可能导致标签条件分布相对于另一个潜在属性不平衡。为了减轻这个问题，我们称之为有条件产生的虚假因果关系，我们提出了一般的两步策略。 （a）公平干预（FI）：强调由于培训数据集中虚假的相关性而难以生成的少数样本。 （b）纠正采样（CS）：明确过滤生成的样品，并确保它们遵循所需的潜在属性分布。我们设计了公平干预措施，以在虚假属性上为各种程度的监督工作，包括无监督，弱监督和半监督的场景。我们的实验结果表明，FIC可以有效地解决各个数据集中有条件产生的虚假因果关系。
To capture the relationship between samples and labels, conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to another latent attribute. To mitigate this issue, which we call spurious causality of conditional generation, we propose a general two-step strategy. (a) Fairness Intervention (FI): emphasize the minority samples that are hard to generate due to the spurious correlation in the training dataset. (b) Corrective Sampling (CS): explicitly filter the generated samples and ensure that they follow the desired latent attribute distribution. We have designed the fairness intervention to work for various degrees of supervision on the spurious attribute, including unsupervised, weakly-supervised, and semi-supervised scenarios. Our experimental results demonstrate that FICS can effectively resolve spurious causality of conditional generation across various datasets.
