Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs

Sümeyye Baş; Kıymet Kaya; Resul Tugay; Şule Gündüz Öğüdücü

doi:10.1007/978-3-032-25311-8_27

Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs

Sümeyye Baş
, Kıymet Kaya^*
, Resul Tugay
, Şule Gündüz Öğüdücü

^*Corresponding author for this work

Department of Artificial Intelligence and Data Engineering

Istanbul Technical University
Application Center
ITU.
BTS Group
Gazi University

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

Abstract

Graphs are crucial for representing interrelated data and aiding predictive modeling by capturing complex relationships. Achieving high-quality graph representation is important for identifying linked patterns, leading to improvements in Graph Neural Networks (GNNs) to better capture data structures. However, challenges such as data scarcity, high collection costs, and ethical concerns limit progress. As a result, generative models and data augmentation have become more and more popular. This study explores using generated graphs for data augmentation, comparing the performance of combining generated graphs with real graphs, and examining the effect of different quantities of generated graphs on graph classification tasks. The experiments show that balancing scalability and quality requires different generators based on graph size. Our results introduce a new approach to graph data augmentation, ensuring consistent labels and enhancing classification performance.

Original language	English
Title of host publication	Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers
Editors	Mattia Cerrato, Danguole Kalinauskaite, Mantas Lukoševicius, Kristina Šutiene, Mykola Pechenizkiy
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	347-358
Number of pages	12
ISBN (Print)	9783032253101
DOIs	https://doi.org/10.1007/978-3-032-25311-8_27
Publication status	Published - 2026
Event	24th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2024 - Vilnius, Lithuania Duration: 9 Sept 2024 → 13 Sept 2024

Publication series

Name	Communications in Computer and Information Science
Volume	2560 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	24th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2024
Country/Territory	Lithuania
City	Vilnius
Period	9/09/24 → 13/09/24

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Keywords

Generative models
Graph neural networks
Graph sequentialization
Data augmentation

Access to Document

10.1007/978-3-032-25311-8_27

Cite this

Baş, S., Kaya, K., Tugay, R., & Öğüdücü, Ş. G. (2026). Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs. In M. Cerrato, D. Kalinauskaite, M. Lukoševicius, K. Šutiene, & M. Pechenizkiy (Eds.), Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers (pp. 347-358). (Communications in Computer and Information Science; Vol. 2560 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-032-25311-8_27

Baş, Sümeyye ; Kaya, Kıymet ; Tugay, Resul et al. / Data Augmentation in Graph Neural Networks : The Role of Generated Synthetic Graphs. Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers. editor / Mattia Cerrato ; Danguole Kalinauskaite ; Mantas Lukoševicius ; Kristina Šutiene ; Mykola Pechenizkiy. Springer Science and Business Media Deutschland GmbH, 2026. pp. 347-358 (Communications in Computer and Information Science).

@inproceedings{b241c7ff16cd427c81f829f3adb7624f,

title = "Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs",

abstract = "Graphs are crucial for representing interrelated data and aiding predictive modeling by capturing complex relationships. Achieving high-quality graph representation is important for identifying linked patterns, leading to improvements in Graph Neural Networks (GNNs) to better capture data structures. However, challenges such as data scarcity, high collection costs, and ethical concerns limit progress. As a result, generative models and data augmentation have become more and more popular. This study explores using generated graphs for data augmentation, comparing the performance of combining generated graphs with real graphs, and examining the effect of different quantities of generated graphs on graph classification tasks. The experiments show that balancing scalability and quality requires different generators based on graph size. Our results introduce a new approach to graph data augmentation, ensuring consistent labels and enhancing classification performance.",

keywords = "Generative models, Graph neural networks, Graph sequentialization, Data augmentation",

author = "S{\"u}meyye Ba{\c s} and Kıymet Kaya and Resul Tugay and {\"O}ğ{\"u}d{\"u}c{\"u}, \{{\c S}ule G{\"u}nd{\"u}z\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 24th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2024 ; Conference date: 09-09-2024 Through 13-09-2024",

year = "2026",

doi = "10.1007/978-3-032-25311-8\_27",

language = "English",

isbn = "9783032253101",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "347--358",

editor = "Mattia Cerrato and Danguole Kalinauskaite and Mantas Luko{\v s}evicius and Kristina {\v S}utiene and Mykola Pechenizkiy",

booktitle = "Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers",

address = "Germany",

}

Baş, S, Kaya, K, Tugay, R & Öğüdücü, ŞG 2026, Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs. in M Cerrato, D Kalinauskaite, M Lukoševicius, K Šutiene & M Pechenizkiy (eds), Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers. Communications in Computer and Information Science, vol. 2560 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 347-358, 24th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2024, Vilnius, Lithuania, 9/09/24. https://doi.org/10.1007/978-3-032-25311-8_27

Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs. / Baş, Sümeyye; Kaya, Kıymet; Tugay, Resul et al.
Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers. ed. / Mattia Cerrato; Danguole Kalinauskaite; Mantas Lukoševicius; Kristina Šutiene; Mykola Pechenizkiy. Springer Science and Business Media Deutschland GmbH, 2026. p. 347-358 (Communications in Computer and Information Science; Vol. 2560 CCIS).

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

TY - GEN

T1 - Data Augmentation in Graph Neural Networks

T2 - 24th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2024

AU - Baş, Sümeyye

AU - Kaya, Kıymet

AU - Tugay, Resul

AU - Öğüdücü, Şule Gündüz

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2026

Y1 - 2026

N2 - Graphs are crucial for representing interrelated data and aiding predictive modeling by capturing complex relationships. Achieving high-quality graph representation is important for identifying linked patterns, leading to improvements in Graph Neural Networks (GNNs) to better capture data structures. However, challenges such as data scarcity, high collection costs, and ethical concerns limit progress. As a result, generative models and data augmentation have become more and more popular. This study explores using generated graphs for data augmentation, comparing the performance of combining generated graphs with real graphs, and examining the effect of different quantities of generated graphs on graph classification tasks. The experiments show that balancing scalability and quality requires different generators based on graph size. Our results introduce a new approach to graph data augmentation, ensuring consistent labels and enhancing classification performance.

AB - Graphs are crucial for representing interrelated data and aiding predictive modeling by capturing complex relationships. Achieving high-quality graph representation is important for identifying linked patterns, leading to improvements in Graph Neural Networks (GNNs) to better capture data structures. However, challenges such as data scarcity, high collection costs, and ethical concerns limit progress. As a result, generative models and data augmentation have become more and more popular. This study explores using generated graphs for data augmentation, comparing the performance of combining generated graphs with real graphs, and examining the effect of different quantities of generated graphs on graph classification tasks. The experiments show that balancing scalability and quality requires different generators based on graph size. Our results introduce a new approach to graph data augmentation, ensuring consistent labels and enhancing classification performance.

KW - Generative models

KW - Graph neural networks

KW - Graph sequentialization

KW - Data augmentation

UR - https://www.scopus.com/pages/publications/105039965247

U2 - 10.1007/978-3-032-25311-8_27

DO - 10.1007/978-3-032-25311-8_27

M3 - Conference contribution

AN - SCOPUS:105039965247

SN - 9783032253101

T3 - Communications in Computer and Information Science

SP - 347

EP - 358

BT - Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers

A2 - Cerrato, Mattia

A2 - Kalinauskaite, Danguole

A2 - Lukoševicius, Mantas

A2 - Šutiene, Kristina

A2 - Pechenizkiy, Mykola

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 9 September 2024 through 13 September 2024

ER -

Baş S, Kaya K, Tugay R, Öğüdücü ŞG. Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs. In Cerrato M, Kalinauskaite D, Lukoševicius M, Šutiene K, Pechenizkiy M, editors, Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2026. p. 347-358. (Communications in Computer and Information Science). doi: 10.1007/978-3-032-25311-8_27