Model-Based Multiple Instance Learning
This work addresses the challenge of handling point pattern data in machine learning, offering a novel statistical approach for researchers in this domain, though it appears incremental as it builds on existing point process theory.
The authors tackled the problem of learning from multiple instance data, which are unordered point patterns, by proposing a model-based framework using point process theory, resulting in principled extensions for classification, novelty detection, and clustering with tractable models and solutions.
While Multiple Instance (MI) data are point patterns -- sets or multi-sets of unordered points -- appropriate statistical point pattern models have not been used in MI learning. This article proposes a framework for model-based MI learning using point process theory. Likelihood functions for point pattern data derived from point process theory enable principled yet conceptually transparent extensions of learning tasks, such as classification, novelty detection and clustering, to point pattern data. Furthermore, tractable point pattern models as well as solutions for learning and decision making from point pattern data are developed.