arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.04881cs.LGstat.ML
收藏

基于图神经网络的多示例学习

Multiple instance learning with graph neural networks

JD AI Research(京东人工智能研究院)

Ming Tu, Jing Huang, Xiaodong He, Bowen Zhou

摘要:

多实例学习(MIL)的目的是学习一个包的实例和包级标签之间的映射。本文提出了一种新的基于端到端图神经网络(GNN)的MIL算法:将每个包视为一个图,使用GNN学习包的嵌入,以探索包中实例之间有用的结构信息。最终的图形表示被馈送到分类器中用于标签预测。我们的算法是第一次尝试使用GNN的MIL。我们的经验表明,该算法实现了几个流行的MIL数据集的最先进的性能,而不会失去模型的可解释性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑