Multi-Label Classification Neural Networks with Hard Logical Constraints
This addresses the challenge of ensuring predictions satisfy subclass relationships in multi-label classification, which is incremental as it builds on existing methods to handle more complex constraints.
The paper tackles hierarchical multi-label classification problems with hard logical constraints by proposing C-HMCNN(h) and CCN(h), which exploit hierarchy information to produce coherent predictions and improve performance, showing superior results compared to state-of-the-art models in extensive experiments.
Multi-label classification (MC) is a standard machine learning problem in which a data point can be associated with a set of classes. A more challenging scenario is given by hierarchical multi-label classification (HMC) problems, in which every prediction must satisfy a given set of hard constraints expressing subclass relationships between classes. In this paper, we propose C-HMCNN(h), a novel approach for solving HMC problems, which, given a network h for the underlying MC problem, exploits the hierarchy information in order to produce predictions coherent with the constraints and to improve performance. Furthermore, we extend the logic used to express HMC constraints in order to be able to specify more complex relations among the classes and propose a new model CCN(h), which extends C-HMCNN(h) and is again able to satisfy and exploit the constraints to improve performance. We conduct an extensive experimental analysis showing the superior performance of both C-HMCNN(h) and CCN(h) when compared to state-of-the-art models in both the HMC and the general MC setting with hard logical constraints.