Interesting Concept Mining With Concept Lattice Convolutional Networks

The extraction of meaningful conceptual structures is often a critical task in many scientific and engineering disciplines, as it enables a comprehensive analysis of complex data in terms of both context and content. In this paper, we introduce the Concept Lattice Convolutional Network (<inline-f...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohamed Hamza Ibrahim, Rokia Missaoui, Pedro Henrique B. Ruas
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11027055/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849469127132971008
author Mohamed Hamza Ibrahim
Rokia Missaoui
Pedro Henrique B. Ruas
author_facet Mohamed Hamza Ibrahim
Rokia Missaoui
Pedro Henrique B. Ruas
author_sort Mohamed Hamza Ibrahim
collection DOAJ
description The extraction of meaningful conceptual structures is often a critical task in many scientific and engineering disciplines, as it enables a comprehensive analysis of complex data in terms of both context and content. In this paper, we introduce the Concept Lattice Convolutional Network (<inline-formula> <tex-math notation="LaTeX">$\mathcal {LCN}$ </tex-math></inline-formula>), an efficient semi-supervised learning approach to identify actionable concepts (i.e., interesting conceptual structures) based on a scalable convolutional neural network architecture that operates on concept lattices. The <inline-formula> <tex-math notation="LaTeX">$\mathcal {LCN}$ </tex-math></inline-formula> captures diverse levels of global context by employing a message-passing mechanism that incorporates local structural and conceptual information within a lattice. It also employs parameter-sharing convolutional operations as conceptual filters to efficiently discern relevant concepts amidst the irrelevant ones. Moreover, it applies consistent aggregations that maintain local consistency of labeling across concepts in the lattice. Experiments on several datasets show that <inline-formula> <tex-math notation="LaTeX">$\mathcal {LCN}$ </tex-math></inline-formula> can accurately identify actionable concepts and is at least three times faster than state-of-the-art exact interestingness indices.
format Article
id doaj-art-63f3b04bbd1d4eacbee46ca450340c3d
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-63f3b04bbd1d4eacbee46ca450340c3d2025-08-20T03:25:38ZengIEEEIEEE Access2169-35362025-01-0113997899980110.1109/ACCESS.2025.357744511027055Interesting Concept Mining With Concept Lattice Convolutional NetworksMohamed Hamza Ibrahim0https://orcid.org/0000-0002-0604-2709Rokia Missaoui1https://orcid.org/0000-0001-7410-4177Pedro Henrique B. Ruas2https://orcid.org/0000-0001-6423-8681Computer Science and Engineering Department, American University of Sharjah, Sharjah, United Arab EmiratesDepartment of Computer Science and Engineering, University of Quebec in Outaouais, Gatineau, QC, CanadaEncora Digital Inc., Campinas, SÃo Paulo, BrazilThe extraction of meaningful conceptual structures is often a critical task in many scientific and engineering disciplines, as it enables a comprehensive analysis of complex data in terms of both context and content. In this paper, we introduce the Concept Lattice Convolutional Network (<inline-formula> <tex-math notation="LaTeX">$\mathcal {LCN}$ </tex-math></inline-formula>), an efficient semi-supervised learning approach to identify actionable concepts (i.e., interesting conceptual structures) based on a scalable convolutional neural network architecture that operates on concept lattices. The <inline-formula> <tex-math notation="LaTeX">$\mathcal {LCN}$ </tex-math></inline-formula> captures diverse levels of global context by employing a message-passing mechanism that incorporates local structural and conceptual information within a lattice. It also employs parameter-sharing convolutional operations as conceptual filters to efficiently discern relevant concepts amidst the irrelevant ones. Moreover, it applies consistent aggregations that maintain local consistency of labeling across concepts in the lattice. Experiments on several datasets show that <inline-formula> <tex-math notation="LaTeX">$\mathcal {LCN}$ </tex-math></inline-formula> can accurately identify actionable concepts and is at least three times faster than state-of-the-art exact interestingness indices.https://ieeexplore.ieee.org/document/11027055/Formal concept analysispattern mininggraph convolutional networkmessage-passinginterestingness measuresemi-supervised learning
spellingShingle Mohamed Hamza Ibrahim
Rokia Missaoui
Pedro Henrique B. Ruas
Interesting Concept Mining With Concept Lattice Convolutional Networks
IEEE Access
Formal concept analysis
pattern mining
graph convolutional network
message-passing
interestingness measure
semi-supervised learning
title Interesting Concept Mining With Concept Lattice Convolutional Networks
title_full Interesting Concept Mining With Concept Lattice Convolutional Networks
title_fullStr Interesting Concept Mining With Concept Lattice Convolutional Networks
title_full_unstemmed Interesting Concept Mining With Concept Lattice Convolutional Networks
title_short Interesting Concept Mining With Concept Lattice Convolutional Networks
title_sort interesting concept mining with concept lattice convolutional networks
topic Formal concept analysis
pattern mining
graph convolutional network
message-passing
interestingness measure
semi-supervised learning
url https://ieeexplore.ieee.org/document/11027055/
work_keys_str_mv AT mohamedhamzaibrahim interestingconceptminingwithconceptlatticeconvolutionalnetworks
AT rokiamissaoui interestingconceptminingwithconceptlatticeconvolutionalnetworks
AT pedrohenriquebruas interestingconceptminingwithconceptlatticeconvolutionalnetworks