Minimal Learning Machine for Multi-Label Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hämäläinen, Joonas, Hubermont, Antoine, Souza, Amauri, Mattos, César L. C., Gomes, João P. P., Kärkkäinen, Tommi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916506393116672
author Hämäläinen, Joonas
Hubermont, Antoine
Souza, Amauri
Mattos, César L. C.
Gomes, João P. P.
Kärkkäinen, Tommi
author_facet Hämäläinen, Joonas
Hubermont, Antoine
Souza, Amauri
Mattos, César L. C.
Gomes, João P. P.
Kärkkäinen, Tommi
contents Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose new methods and evaluate how their core component, the distance mapping, can be adapted to multi-label learning. The proposed approach is based on combining the distance mapping with an inverse distance weighting. Although the proposal is one of the simplest methods in the multi-label learning literature, it achieves state-of-the-art performance for small to moderate-sized multi-label learning problems. In addition to its simplicity, the proposed method is fully deterministic: Its hyper-parameter can be selected via ranking loss-based statistic which has a closed form, thus avoiding conventional cross-validation-based hyper-parameter tuning. In addition, due to its simple linear distance mapping-based construction, we demonstrate that the proposed method can assess the uncertainty of the predictions for multi-label classification, which is a valuable capability for data-centric machine learning pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2305_05518
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Minimal Learning Machine for Multi-Label Learning
Hämäläinen, Joonas
Hubermont, Antoine
Souza, Amauri
Mattos, César L. C.
Gomes, João P. P.
Kärkkäinen, Tommi
Machine Learning
Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose new methods and evaluate how their core component, the distance mapping, can be adapted to multi-label learning. The proposed approach is based on combining the distance mapping with an inverse distance weighting. Although the proposal is one of the simplest methods in the multi-label learning literature, it achieves state-of-the-art performance for small to moderate-sized multi-label learning problems. In addition to its simplicity, the proposed method is fully deterministic: Its hyper-parameter can be selected via ranking loss-based statistic which has a closed form, thus avoiding conventional cross-validation-based hyper-parameter tuning. In addition, due to its simple linear distance mapping-based construction, we demonstrate that the proposed method can assess the uncertainty of the predictions for multi-label classification, which is a valuable capability for data-centric machine learning pipelines.
title Minimal Learning Machine for Multi-Label Learning
topic Machine Learning
url https://arxiv.org/abs/2305.05518