When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also its context in the corresponding bag. From the viewpoint of causal inference, such bag contextual prior works as a confounder and may result in model robustness and interpretability issues. Focusing on this problem, we propose a novel interventional multi-instance learning (IMIL) framework to achieve deconfounded instance-level prediction. Unlike traditional likelihood-based strategies, we design an Expectation-Maximization (EM) algorithm based on causal intervention, providing a robust instance selection in the training phase and suppressing the bias caused by the bag contextual prior. Experiments on pathological image analysis demonstrate that our IMIL method substantially reduces false positives and outperforms state-of-the-art MIL methods.
翻译:在应用多因子学习(MIL)来预测一袋实例时,一个实例的预测准确性往往不仅取决于实例本身,而且取决于其相应包中的背景。从因果推断的角度来看,这种包型背景先前的工作是混乱的,可能导致模型的稳健性和可解释性问题。我们关注这一问题,提出一个新的干预性多因子学习(IMIL)框架,以实现无根据的例级预测。与传统的基于可能性的战略不同,我们设计了基于因果干预的预期-最大化算法,在培训阶段提供了强有力的实例选择,并抑制了包型背景先前造成的偏见。病理图像分析实验表明,我们的IMIL方法极大地减少了假正数,并超越了现代的MIL方法。