A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For image classifiers, augmenting a training dataset using counterfactual examples has been empirically shown to break spurious correlations. However, the counterfactual generation task itself becomes more difficult as the level of confounding increases. Existing methods for counterfactual generation under confounding consider a fixed set of interventions (e.g., texture, rotation) and are not flexible enough to capture diverse data-generating processes. Given a causal generative process, we formally characterize the adverse effects of confounding on any downstream tasks and show that the correlation between generative factors (attributes) can be used to quantitatively measure confounding between generative factors. To minimize such correlation, we propose a counterfactual generation method that learns to modify the value of any attribute in an image and generate new images given a set of observed attributes, even when the dataset is highly confounded. These counterfactual images are then used to regularize the downstream classifier such that the learned representations are the same across various generative factors conditioned on the class label. Our method is computationally efficient, simple to implement, and works well for any number of generative factors and confounding variables. Our experimental results on both synthetic (MNIST variants) and real-world (CelebA) datasets show the usefulness of our approach.
翻译:机器学习模型,在培训数据中观测到或未观察到的混淆者的影响下,可以学习假的关联性,在部署时无法概括。对于图像分类者来说,用反事实实例来增加培训数据集的经验显示会打破假的关联性。然而,反事实生成任务本身随着混乱程度的提高而变得更加困难。在混淆的情况下,反事实生成的现有方法会考虑固定的一套干预措施(例如,纹理、旋转),而且不够灵活,无法捕捉不同的数据生成过程。鉴于因果关系的基因变异过程,我们正式描述在任何下游任务上混结的不利效应,并表明可使用基因变异因素(因素)之间的关联性来定量测量基因变异因素之间的混杂性。为了尽量减少这种关联性,我们提出了一种反事实生成方法,即学会改变图像中任何属性的价值,并产生新图像,给一组观察到的属性,即使数据集非常相似。这些反事实图像随后被用来将下游的分类对下游变异基因变异性结果进行调节,因此,我们所了解的变异性变异性模型的变异性变异性数据在各种基因变的变异性模型上都显示。