论文标题
介入的多个实体学习，具有解浓度的实例级别的预测
Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction
论文作者
论文摘要
当应用多实体学习（MIL）对实例袋进行预测时，实例的预测准确性通常不仅取决于实例本身，而且还取决于相应袋中的上下文。从因果推断的角度来看，这种行李上下文的先验作品是混杂的，可能会导致模型的鲁棒性和可解释性问题。为了关注这个问题，我们提出了一种新颖的介入性多构度学习（IMIL）框架，以实现脱连的实例级别的预测。与传统的基于可能性的策略不同，我们根据因果干预设计了一种期望最大化（EM）算法，在培训阶段提供了强大的实例选择，并抑制了袋子上下文造成的偏见。关于病理图像分析的实验表明，我们的IMIL方法大大降低了误报，并且表现优于最先进的MIL方法。
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.
