Instance Label Prediction by Dirichlet Process Multiple Instance Learning
Melih Kandemir, Fred A. Hamprecht · 2014
We propose a generative Bayesian model that predicts instance labels from weak (bag-level) supervision. We solve this problem by simulta-neously modeling class distributions by Gaussian mixture models and inferring the class labels of positive bag instances that satisfy the multiple in-stance constraints. We employ Dirichlet process priors on mixture weights to automate model se-lection, and efficiently infer model parameters and positive bag instances by a constrained varia-tional Bayes procedure. Our method improves on the state-of-the-art of instance classification from weak supervision on 20 benchmark text catego-rization data sets and one histopathology cancer diagnosis data set. 1