Model Agnostic Interpretability for Multiple Instance Learning. (arXiv:2201.11701v1 [cs.LG])

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 …

arxiv interpretability learning