Using Neural Network Formalism to Solve Multiple-Instance Problems

TL;DR

This paper introduces a neural network formalism for multiple-instance learning that effectively models set-based objects, enabling pattern discovery and improved accuracy over existing classifiers on benchmark datasets.

Contribution

A novel neural network formalism for MIL that bridges traditional MIL problems with standard neural models, optimized via modified back-propagation.

Findings

Effective optimization with modified back-propagation.

Outperforms eight prior classifiers on 14 benchmark datasets.

Reveals unknown patterns within bags.

Abstract

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.