Multi-feature Subgraph Fusion with Text Knowledge on Citation Link Prediction

Ghaluh Indah Permata Sari; Hsing Kuo Pao; Rudy Cahyadi Hario Pribadi; Mohammad Iqbal

doi:10.1007/978-981-97-2136-8_22

Multi-feature Subgraph Fusion with Text Knowledge on Citation Link Prediction

Ghaluh Indah Permata Sari, Hsing Kuo Pao, Rudy Cahyadi Hario Pribadi, Mohammad Iqbal^*

^*Corresponding author for this work

Laboratory of Machine Learning and Big Data

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We propose multi-feature subgraph fusion neural networks to predict the citation links. We aim to refine the sparsity of the subgraph feature of citation links among articles. The proposed model fuses four features: subgraph of social network metrics, metadata article info, Word2Vec, and tf-IDF of the articles. Basically, we focus on the edge list feature level instead of the graph level since we can avoid the heavy computation for the adjacency matrix. However, we may neglect the similarity between articles in the text domain. Henceforth, we fuse with text knowledge from the articles, such as the corpus embedding and metadata of the articles. The proposed model was evaluated on a public dataset for link prediction. We can enjoy the proposed model performances by showing the ablation study on the fusion feature(s).

Original language	English
Title of host publication	Applied and Computational Mathematics - ICoMPAC 2023
Editors	Dieky Adzkiya, Kistosil Fahim
Publisher	Springer
Pages	299-308
Number of pages	10
ISBN (Print)	9789819721351
DOIs	https://doi.org/10.1007/978-981-97-2136-8_22
Publication status	Published - 2024
Event	8th International Conference on Mathematics: Pure, Applied and Computation, ICoMPAC 2023 - Lombok, Indonesia Duration: 30 Sept 2023 → 30 Sept 2023

Publication series

Name	Springer Proceedings in Mathematics and Statistics
Volume	455
ISSN (Print)	2194-1009
ISSN (Electronic)	2194-1017

Conference

Conference	8th International Conference on Mathematics: Pure, Applied and Computation, ICoMPAC 2023
Country/Territory	Indonesia
City	Lombok
Period	30/09/23 → 30/09/23

Keywords

Citation network
Feature fusion
Graph neural network
Link prediction

Access to Document

10.1007/978-981-97-2136-8_22

Cite this

@inproceedings{95bee9e00ac14bf4a046bc0d3725ab1d,

title = "Multi-feature Subgraph Fusion with Text Knowledge on Citation Link Prediction",

abstract = "We propose multi-feature subgraph fusion neural networks to predict the citation links. We aim to refine the sparsity of the subgraph feature of citation links among articles. The proposed model fuses four features: subgraph of social network metrics, metadata article info, Word2Vec, and tf-IDF of the articles. Basically, we focus on the edge list feature level instead of the graph level since we can avoid the heavy computation for the adjacency matrix. However, we may neglect the similarity between articles in the text domain. Henceforth, we fuse with text knowledge from the articles, such as the corpus embedding and metadata of the articles. The proposed model was evaluated on a public dataset for link prediction. We can enjoy the proposed model performances by showing the ablation study on the fusion feature(s).",

keywords = "Citation network, Feature fusion, Graph neural network, Link prediction",

author = "Sari, {Ghaluh Indah Permata} and Pao, {Hsing Kuo} and Pribadi, {Rudy Cahyadi Hario} and Mohammad Iqbal",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 8th International Conference on Mathematics: Pure, Applied and Computation, ICoMPAC 2023 ; Conference date: 30-09-2023 Through 30-09-2023",

year = "2024",

doi = "10.1007/978-981-97-2136-8_22",

language = "English",

isbn = "9789819721351",

series = "Springer Proceedings in Mathematics and Statistics",

publisher = "Springer",

pages = "299--308",

editor = "Dieky Adzkiya and Kistosil Fahim",

booktitle = "Applied and Computational Mathematics - ICoMPAC 2023",

address = "Germany",

}

Sari, GIP, Pao, HK, Pribadi, RCH & Iqbal, M 2024, Multi-feature Subgraph Fusion with Text Knowledge on Citation Link Prediction. in D Adzkiya & K Fahim (eds), Applied and Computational Mathematics - ICoMPAC 2023. Springer Proceedings in Mathematics and Statistics, vol. 455, Springer, pp. 299-308, 8th International Conference on Mathematics: Pure, Applied and Computation, ICoMPAC 2023, Lombok, Indonesia, 30/09/23. https://doi.org/10.1007/978-981-97-2136-8_22

Multi-feature Subgraph Fusion with Text Knowledge on Citation Link Prediction. / Sari, Ghaluh Indah Permata; Pao, Hsing Kuo; Pribadi, Rudy Cahyadi Hario et al.
Applied and Computational Mathematics - ICoMPAC 2023. ed. / Dieky Adzkiya; Kistosil Fahim. Springer, 2024. p. 299-308 (Springer Proceedings in Mathematics and Statistics; Vol. 455).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multi-feature Subgraph Fusion with Text Knowledge on Citation Link Prediction

AU - Sari, Ghaluh Indah Permata

AU - Pao, Hsing Kuo

AU - Pribadi, Rudy Cahyadi Hario

AU - Iqbal, Mohammad

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - We propose multi-feature subgraph fusion neural networks to predict the citation links. We aim to refine the sparsity of the subgraph feature of citation links among articles. The proposed model fuses four features: subgraph of social network metrics, metadata article info, Word2Vec, and tf-IDF of the articles. Basically, we focus on the edge list feature level instead of the graph level since we can avoid the heavy computation for the adjacency matrix. However, we may neglect the similarity between articles in the text domain. Henceforth, we fuse with text knowledge from the articles, such as the corpus embedding and metadata of the articles. The proposed model was evaluated on a public dataset for link prediction. We can enjoy the proposed model performances by showing the ablation study on the fusion feature(s).

AB - We propose multi-feature subgraph fusion neural networks to predict the citation links. We aim to refine the sparsity of the subgraph feature of citation links among articles. The proposed model fuses four features: subgraph of social network metrics, metadata article info, Word2Vec, and tf-IDF of the articles. Basically, we focus on the edge list feature level instead of the graph level since we can avoid the heavy computation for the adjacency matrix. However, we may neglect the similarity between articles in the text domain. Henceforth, we fuse with text knowledge from the articles, such as the corpus embedding and metadata of the articles. The proposed model was evaluated on a public dataset for link prediction. We can enjoy the proposed model performances by showing the ablation study on the fusion feature(s).

KW - Citation network

KW - Feature fusion

KW - Graph neural network

KW - Link prediction

UR - http://www.scopus.com/inward/record.url?scp=85200697258&partnerID=8YFLogxK

U2 - 10.1007/978-981-97-2136-8_22

DO - 10.1007/978-981-97-2136-8_22

M3 - Conference contribution

AN - SCOPUS:85200697258

SN - 9789819721351

T3 - Springer Proceedings in Mathematics and Statistics

SP - 299

EP - 308

BT - Applied and Computational Mathematics - ICoMPAC 2023

A2 - Adzkiya, Dieky

A2 - Fahim, Kistosil

PB - Springer

T2 - 8th International Conference on Mathematics: Pure, Applied and Computation, ICoMPAC 2023

Y2 - 30 September 2023 through 30 September 2023

ER -