Multiple instance learning with graph neural networks

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.

[1]  Max Welling,et al.  Attention-based Deep Multiple Instance Learning , 2018, ICML.

[2]  Mirella Lapata,et al.  Multiple Instance Learning Networks for Fine-Grained Sentiment Analysis , 2017, TACL.

[3]  Jan Ramon,et al.  Multi instance neural networks , 2000, ICML 2000.

[4]  Murat Dundar,et al.  Bayesian multiple instance learning: automatic feature selection and inductive transfer , 2008, ICML '08.

[5]  Yixin Chen,et al.  MILES: Multiple-Instance Learning via Embedded Instance Selection , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Zhi-Hua Zhou,et al.  Multi-instance learning by treating instances as non-I.I.D. samples , 2008, ICML '09.

[7]  Marco Loog,et al.  Dissimilarity-Based Ensembles for Multiple Instance Learning , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[8]  James R. Foulds,et al.  Revisiting Multiple-Instance Learning Via Embedded Instance Selection , 2008, Australasian Conference on Artificial Intelligence.

[9]  Visar Berisha,et al.  Objective assessment of pathological speech using distribution regression , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Jun Wang,et al.  Solving the Multiple-Instance Problem: A Lazy Learning Approach , 2000, ICML.

[11]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[12]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[13]  Zhi-Hua Zhou,et al.  On the relation between multi-instance learning and semi-supervised learning , 2007, ICML '07.

[14]  Laude,et al.  FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE , 2014 .

[15]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[16]  Wenyu Liu,et al.  Revisiting multiple instance neural networks , 2016, Pattern Recognit..

[17]  Zhuowen Tu,et al.  Deeply-Supervised Nets , 2014, AISTATS.

[18]  Melih Kandemir,et al.  Computer-aided diagnosis from weak supervision: A benchmarking study , 2015, Comput. Medical Imaging Graph..

[19]  Jure Leskovec,et al.  Hierarchical Graph Representation Learning with Differentiable Pooling , 2018, NeurIPS.