Boundary heat diffusion classifier for a semi-supervised
learning in a multilayer network embedding

J 2022

Boundary heat diffusion classifier for a semi-supervised learning in a multilayer network embedding

TIMILSINA, Mohan, Vít NOVÁČEK, Mathieu DAQUIN and Haixuan YANG

Basic information

Original name

Boundary heat diffusion classifier for a semi-supervised learning in a multilayer network embedding

Name in Czech

Boundary heat diffusion classifier for a semi-supervised learning in a multilayer network embedding

Authors

TIMILSINA, Mohan, Vít NOVÁČEK (203 Czech Republic, guarantor, belonging to the institution), Mathieu DAQUIN and Haixuan YANG

Edition

NEURAL NETWORKS, ENGLAND, PERGAMON-ELSEVIER SCIENCE LTD, 2022, 0893-6080

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Netherlands

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

original online article

Impact factor

Impact factor: 7.800

RIV identification code

RIV/00216224:14330/22:00127569

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1016/j.neunet.2022.10.005

UT WoS

000886066900007

Keywords in English

diffusion; multi-layer embedding; neural network

Abstract

V originále

The scarcity of high-quality annotations in many application scenarios has recently led to an increasing interest in devising learning techniques that combine unlabeled data with labeled data in a network. In this work, we focus on the label propagation problem in multilayer networks. Our approach is inspired by the heat diffusion model, which shows usefulness in machine learning problems such as classification and dimensionality reduction. We propose a novel boundary-based heat diffusion algorithm that guarantees a closed-form solution with an efficient implementation. We experimentally validated our method on synthetic networks and five real-world multilayer network datasets representing scientific coauthorship, spreading drug adoption among physicians, two bibliographic networks, and a movie network. The results demonstrate the benefits of the proposed algorithm, where our boundary-based heat diffusion dominates the performance of the state-of-the-art methods.

Citovat

TIMILSINA, Mohan, Vít NOVÁČEK, Mathieu DAQUIN and Haixuan YANG. Boundary heat diffusion classifier for a semi-supervised learning in a multilayer network embedding. NEURAL NETWORKS. ENGLAND: PERGAMON-ELSEVIER SCIENCE LTD, 2022, vol. 156, No 1, p. 205-217. ISSN 0893-6080. Available from: https://dx.doi.org/10.1016/j.neunet.2022.10.005.

@article{2241658,
   author = {Timilsina, Mohan and Nováček, Vít and dAquin, Mathieu and Yang, Haixuan},
   article_location = {ENGLAND},
   article_number = {1},
   doi = {http://dx.doi.org/10.1016/j.neunet.2022.10.005},
   keywords = {diffusion; multi-layer embedding; neural network},
   language = {eng},
   issn = {0893-6080},
   journal = {NEURAL NETWORKS},
   title = {Boundary heat diffusion classifier for a semi-supervised learning in a multilayer network embedding},
   url = {https://www.sciencedirect.com/science/article/pii/S0893608022003896},
   volume = {156},
   year = {2022}
}

TY  - JOUR
ID  - 2241658
AU  - Timilsina, Mohan - Nováček, Vít - dAquin, Mathieu - Yang, Haixuan
PY  - 2022
TI  - Boundary heat diffusion classifier for a semi-supervised learning in a multilayer network embedding
JF  - NEURAL NETWORKS
VL  - 156
IS  - 1
SP  - 205-217
EP  - 205-217
PB  - PERGAMON-ELSEVIER SCIENCE LTD
SN  - 08936080
KW  - diffusion
KW  - multi-layer embedding
KW  - neural network
UR  - https://www.sciencedirect.com/science/article/pii/S0893608022003896
N2  - The scarcity of high-quality annotations in many application scenarios has recently led to an increasing interest in devising learning techniques that combine unlabeled data with labeled data in a network. In this work, we focus on the label propagation problem in multilayer networks. Our approach is inspired by the heat diffusion model, which shows usefulness in machine learning problems such as classification and dimensionality reduction. We propose a novel boundary-based heat diffusion algorithm that guarantees a closed-form solution with an efficient implementation. We experimentally validated our method on synthetic networks and five real-world multilayer network datasets representing scientific coauthorship, spreading drug adoption among physicians, two bibliographic networks, and a movie network. The results demonstrate the benefits of the proposed algorithm, where our boundary-based heat diffusion dominates the performance of the state-of-the-art methods.
ER  -

TIMILSINA, Mohan, Vít NOVÁČEK, Mathieu DAQUIN and Haixuan YANG. Boundary heat diffusion classifier for a semi-supervised learning in a multilayer network embedding. \textit{NEURAL NETWORKS}. ENGLAND: PERGAMON-ELSEVIER SCIENCE LTD, 2022, vol.~156, No~1, p.~205-217. ISSN~0893-6080. Available from: https://dx.doi.org/10.1016/j.neunet.2022.10.005.

Detailed Information on Publication Record