Model Agnostic Interpretability for Multiple Instance Learning
This work addresses interpretability challenges in MIL for applications like medical imaging or text classification, though it appears incremental as it builds on existing interpretable models.
The paper tackled the problem of interpreting Multiple Instance Learning models, which classify bags of instances with single labels, by developing model-agnostic methods that increase interpretability accuracy by up to 30% compared to existing interpretable models.
In Multiple Instance Learning (MIL), models are trained using bags of instances, where only a single label is provided for each bag. A bag label is often only determined by a handful of key instances within a bag, making it difficult to interpret what information a classifier is using to make decisions. In this work, we establish the key requirements for interpreting MIL models. We then go on to develop several model-agnostic approaches that meet these requirements. Our methods are compared against existing inherently interpretable MIL models on several datasets, and achieve an increase in interpretability accuracy of up to 30%. We also examine the ability of the methods to identify interactions between instances and scale to larger datasets, improving their applicability to real-world problems.