Imbalanced Multi-instance Data

Class imbalance is widely studied in single-instance learning and refers to the situation where the data observations are unevenly distributed among the possible classes. This phenomenon can present itself in MIL as well. Section 9.1 presents a general introduction to the topic of class imbalance, list the types of solutions to deal with it, and the appropriate performance metrics. In Sect. 9.2, we recall a popular single-instance method addressing class imbalance. We provide a detailed specification of multi-instance class imbalance in Sect. 9.3 and discuss its solutions in Sect. 9.4 on resampling methods and in Sect. 9.5 on custom classification methods. Section 9.6 presents the experimental analysis accompanying this chapter. Some summarizing remarks are listed in Sect. 9.7.