TY - GEN
T1 - Performance Analysis of Graph Laplacian Matrices in Node Classification
AU - Dai, Chuan
AU - Wei, Yajuan
AU - Xu, Zhijie
AU - Chen, Minsi
AU - Liu, Ying
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - Graph neural networks have received great attention in recent years due to their wide range of applications. In particular, the use of graph convolutional networks to deal with classification tasks has seen rapid advancements recently. This paper explores a critical step in processing input data for graph convolutional networks, the so-called “normalization of the graph Laplacian matrix”. Two commonly used graph Laplacian matrices normalization schemes, symmetric normalized Laplacian matrix and random walk normalized Laplacian matrix, are analyzed and compared in this research. Critical discoveries are explained through experiments and benchmarking evaluation. The result shows that the symmetric normalized Laplacian matrix is suitable for denser graphs, while the random walk normalized Laplacian matrix is more feasible for sparser graph-based operations.
AB - Graph neural networks have received great attention in recent years due to their wide range of applications. In particular, the use of graph convolutional networks to deal with classification tasks has seen rapid advancements recently. This paper explores a critical step in processing input data for graph convolutional networks, the so-called “normalization of the graph Laplacian matrix”. Two commonly used graph Laplacian matrices normalization schemes, symmetric normalized Laplacian matrix and random walk normalized Laplacian matrix, are analyzed and compared in this research. Critical discoveries are explained through experiments and benchmarking evaluation. The result shows that the symmetric normalized Laplacian matrix is suitable for denser graphs, while the random walk normalized Laplacian matrix is more feasible for sparser graph-based operations.
KW - Graph convolutional networks
KW - Random walk normalized Laplacian matrix
KW - Symmetric normalized Laplacian matrix
UR - http://www.scopus.com/inward/record.url?scp=85195560885&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-49421-5_72
DO - 10.1007/978-3-031-49421-5_72
M3 - Conference Proceeding
AN - SCOPUS:85195560885
SN - 9783031494208
T3 - Mechanisms and Machine Science
SP - 877
EP - 885
BT - Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2
A2 - Ball, Andrew D.
A2 - Wang, Zuolu
A2 - Ouyang, Huajiang
A2 - Sinha, Jyoti K.
PB - Springer Science and Business Media B.V.
T2 - UNIfied Conference of International Workshop on Defence Applications of Multi-Agent Systems, DAMAS 2023, International Conference on Maintenance Engineering, IncoME-V 2023, International conference on the Efficiency and Performance Engineering Network, TEPEN 2023
Y2 - 29 August 2023 through 1 September 2023
ER -