Multiple Instance Learning

Multiple Instance Learning is a type of weakly supervised learning algorithm where training data is arranged in bags, where each bag contains a set of instances $X=\\{x_1,x_2, \ldots,x_M\\}$, and there is one single label $Y$ per bag, $Y\in\\{0, 1\\}$ in the case of a binary classification problem. It is assumed that individual labels $y_1, y_2,\ldots, y_M$ exist for the instances within a bag, but they are unknown during training. In the standard Multiple Instance assumption, a bag is considered negative if all its instances are negative. On the other hand, a bag is positive, if at least one instance in the bag is positive.

Source: Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification