A Hierarchical Multi-Output Nearest Neighbor Model for Multi-Output Dependence Learning

TL;DR

This paper introduces HMONN, a hierarchical nearest neighbor model designed for multi-output dependence learning, addressing the challenge of multiple correct outputs per input by combining basic models with a refined neighbor approach.

Contribution

The paper proposes a novel hierarchical multi-output nearest neighbor model specifically designed for multi-output dependence learning, a problem not addressed by previous algorithms.

Findings

HMONN effectively models multiple correct outputs for a given input.

The approach improves prediction accuracy over traditional methods.

HMONN demonstrates applicability to complex multi-output dependence tasks.

Abstract

Multi-Output Dependence (MOD) learning is a generalization of standard classification problems that allows for multiple outputs that are dependent on each other. A primary issue that arises in the context of MOD learning is that for any given input pattern there can be multiple correct output patterns. This changes the learning task from function approximation to relation approximation. Previous algorithms do not consider this problem, and thus cannot be readily applied to MOD problems. To perform MOD learning, we introduce the Hierarchical Multi-Output Nearest Neighbor model (HMONN) that employs a basic learning model for each output and a modified nearest neighbor approach to refine the initial results.