Multiple instance learning with graph neural networks
This addresses MIL for applications like medical imaging or text classification, but it is incremental as it applies GNNs to an existing problem.
The paper tackles the problem of multiple instance learning (MIL) by proposing a new graph neural network (GNN) algorithm that treats each bag as a graph to learn embeddings, achieving state-of-the-art performance on several popular datasets.
Multiple instance learning (MIL) aims to learn the mapping between a bag of instances and the bag-level label. In this paper, we propose a new end-to-end graph neural network (GNN) based algorithm for MIL: we treat each bag as a graph and use GNN to learn the bag embedding, in order to explore the useful structural information among instances in bags. The final graph representation is fed into a classifier for label prediction. Our algorithm is the first attempt to use GNN for MIL. We empirically show that the proposed algorithm achieves the state of the art performance on several popular MIL data sets without losing model interpretability.