1. A co‐training ‐based approach for the hierarchical multi‐label classification of research papers
- Author
-
Khalil Drira, Hatem Bellaaj, Abir Masmoudi, Mohamed Jmaiel, Université de Sfax - University of Sfax, Équipe Services et Architectures pour Réseaux Avancés (LAAS-SARA), Laboratoire d'analyse et d'architecture des systèmes (LAAS), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Unité de Recherche en développement et contrôle d'applications distribuées (REDCAD), École Nationale d'Ingénieurs de Sfax | National School of Engineers of Sfax (ENIS), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), and Université de Toulouse (UT)
- Subjects
0209 industrial biotechnology ,Computer science ,02 engineering and technology ,Semi-supervised learning ,Imbalanced data ,[INFO.INFO-SE]Computer Science [cs]/Software Engineering [cs.SE] ,Hierarchical Multi-label classication ,Machine learning ,computer.software_genre ,Theoretical Computer Science ,Set (abstract data type) ,Consistency (database systems) ,[INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI] ,020901 industrial engineering & automation ,Cardinality ,Co-training ,Artificial Intelligence ,0202 electrical engineering, electronic engineering, information engineering ,Multi-label classification ,Hierarchy (mathematics) ,business.industry ,[INFO.INFO-WB]Computer Science [cs]/Web ,Research papers classication ,Bibliographic coupling ,ComputingMethodologies_PATTERNRECOGNITION ,Computational Theory and Mathematics ,Control and Systems Engineering ,020201 artificial intelligence & image processing ,[INFO.INFO-ET]Computer Science [cs]/Emerging Technologies [cs.ET] ,Artificial intelligence ,business ,computer - Abstract
International audience; This paper focuses on the problem of the hierarchical multi‐label classification of research papers, which is the task of assigning the set of relevant labels for a paper from a hierarchy, using reduced amounts of labelled training data. Specifically, we study leveraging unlabelled data, which are usually plentiful and easy to collect, in addition to the few available labelled ones in a semi‐supervised learning framework for achieving better performance results. Thus, in this paper, we propose a semi‐supervised approach for the hierarchical multi‐label classification task of research papers based on the well‐known Co‐training algorithm, which exploit content and bibliographic coupling information as two distinct papers' views. In our approach, two hierarchical multi‐label classifiers, are learnt on different views of the labelled data, and iteratively select their most confident unlabelled samples, which are further added to the labelled set. The success of our suggested Co‐training‐based approach lies in two main components. The first is the use of two suggested selection criteria (i.e., Maximum Agreement and Labels Cardinality Consistency) that enforce selecting confident unlabelled samples. The second is the appliance of an oversampling method that rebalances the labels distribution of the initial labelled set, which reduces the reinforcement of the label imbalance issue during the Co‐training learning. The proposed approach is evaluated using a collection of scientific papers extracted from the ACM digital library. Performed experiments show the effectiveness of our approach with regards to several baseline methods.
- Published
- 2021