Class-Dependent Dissimilarity Measures for Multiple Instance Learning

Abstract

Multiple Instance Learning (MIL) is concerned with learning from sets (bags) of feature vectors (instances), where the individual instance labels are ambiguous. In MIL it is often assumed that positive bags contain at least one instance from a so-called concept in instance space, whereas negative bags only contain negative instances. The classes in a MIL problem are therefore not treated in the same manner. One of the ways to classify bags in MIL problems is through the use of bag dissimilarity measures. In current dissimilarity approaches, such dissimilarity measures act on the bag as a whole and do not distinguish between positive and negative bags. In this paper we explore whether this is a reasonable approach and when and why a dissimilarity measure that is dependent on the bag label, might be more appropriate.KeywordsDissimilarity MeasurePositive InstanceInductive Logic ProgrammingMultiple Instance LearnPrototype SelectionThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.