CascadeML: An Automatic Neural Network Architecture Evolution and Training Algorithm for Multi-label Classification

Files in This Item:
File Description SizeFormat 
insight_publication.pdf850.07 kBAdobe PDFDownload
Title: CascadeML: An Automatic Neural Network Architecture Evolution and Training Algorithm for Multi-label Classification
Authors: Pakrashi, ArjunMacNamee, Brian
Permanent link:
Date: 19-Nov-2019
Online since: 2020-11-06T16:57:46Z
Abstract: In multi-label classification a datapoint can be labelled with more than one class at the same time. A common but trivial approach to multi-label classification is to train individual binary classifiers per label, but the performance can be improved by considering associations between the labels, and algorithms like classifier chains and RAKEL do this effectively. Like most machine learning algorithms, however, these approaches require accurate hyperparameter tuning, a computationally expensive optimisation problem. Tuning is important to train a good multi-label classifier model. There is a scarcity in the literature of effective multi-label classification approaches that do not require extensive hyperparameter tuning. This paper addresses this scarcity by proposing CascadeML, a multi-label classification approach based on cascade neural network that takes label associations into account and requires minimal hyperparameter tuning. The performance of the CasecadeML approach is evaluated using 10 multi-label datasets and compared with other leading multi-label classification algorithms. Results show that CascadeML performs comparatively with the leading approaches but without a need for hyperparameter tuning.
Funding Details: Science Foundation Ireland
metadata.dc.description.othersponsorship: Insight Research Centre
Type of material: Conference Publication
Series/Report no.: Lecture Notes in Computer Science; 11927; Lecture Notes in Artificial Intelligence; 11927
Copyright (published version): 2019 Springer
Keywords: Machine learningMulti-label classificationCascade neural networks
DOI: 10.1007/978-3-030-34885-4_1
Other versions:
Language: en
Status of Item: Peer reviewed
Is part of: Bramer, M. and Petridis, M. (eds.). Artificial Intelligence XXXVI: 39th SGAI International Conference on Artificial Intelligence, AI 2019, Cambridge, UK, December 17–19, 2019, Proceedings
Conference Details: The 39th SGAI International Conference on Artificial Intelligence (AI 2019), Cambridge, United Kingdom, 17-19 December 2019
ISBN: 978-3-030-34884-7
Appears in Collections:Insight Research Collection

Show full item record

Page view(s)

Last Week
Last month
checked on Nov 30, 2020


checked on Nov 30, 2020

Google ScholarTM



This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.