Multiple instance learning with graph neural networks

TL;DR

This paper introduces a novel end-to-end graph neural network approach for multiple instance learning, treating each bag as a graph to leverage structural information among instances, achieving state-of-the-art results.

Contribution

It is the first to apply GNNs to MIL, enabling the use of graph structures for improved bag embedding and classification.

Findings

Achieves state-of-the-art performance on MIL datasets.

Maintains model interpretability.

Demonstrates effectiveness of GNNs in MIL tasks.

Abstract

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.