Using Neural Network Formalism to Solve Multiple-Instance Problems
This work addresses the challenge of learning from complex, set-structured data in MIL, which is incremental as it adapts neural networks to an existing problem setting.
The authors tackled the problem of multiple-instance learning (MIL), where objects are represented as bags of instances with labels only at the bag level, by proposing a neural network formalism that bridges MIL with standard models. They demonstrated its effectiveness through optimization via modified back-propagation and achieved accuracy advantages over eight prior classifiers on 14 benchmark datasets.
Many objects in the real world are difficult to describe by a single numerical vector of a fixed length, whereas describing them by a set of vectors is more natural. Therefore, Multiple instance learning (MIL) techniques have been constantly gaining on importance throughout last years. MIL formalism represents each object (sample) by a set (bag) of feature vectors (instances) of fixed length where knowledge about objects (e.g., class label) is available on bag level but not necessarily on instance level. Many standard tools including supervised classifiers have been already adapted to MIL setting since the problem got formalized in late nineties. In this work we propose a neural network (NN) based formalism that intuitively bridges the gap between MIL problem definition and the vast existing knowledge-base of standard models and classifiers. We show that the proposed NN formalism is effectively optimizable by a modified back-propagation algorithm and can reveal unknown patterns inside bags. Comparison to eight types of classifiers from the prior art on a set of 14 publicly available benchmark datasets confirms the advantages and accuracy of the proposed solution.