Multi-Label Classification Neural Networks with Hard Logical Constraints

TL;DR

This paper introduces novel neural network models, C-HMCNN(h) and CCN(h), that incorporate hierarchical logical constraints into multi-label classification, improving prediction coherence and performance over existing methods.

Contribution

The paper presents new neural network architectures that explicitly encode hierarchical constraints in multi-label classification, extending logic for complex class relations.

Findings

C-HMCNN(h) and CCN(h) outperform state-of-the-art models in HMC tasks.

Models produce predictions consistent with hierarchical constraints.

Experimental results show improved accuracy and coherence.

Abstract

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.