Next Article in Journal
Assessment of Dispersion and Bubble Entropy Measures for Enhancing Preterm Birth Prediction Based on Electrohysterographic Signals
Previous Article in Journal
A Temperature-Compensation Technique for Improving Resolver Accuracy
Article

Hierarchical Pooling in Graph Neural Networks to Enhance Classification Performance in Large Datasets

by 1,*, 1 and 2
1
School of Information and Communication Technology, Hanoi University of Science and Technology, 1 Dai Co Viet, Le Dai Hanh, Hai Ba Trung, Hanoi City 10000, Vietnam
2
School of Information Science and Engineering, Lanzhou University, Feiyun Building, 222 Tianshui S Rd, Chengguan Qu, Lanzhou 730030, China
*
Author to whom correspondence should be addressed.
Academic Editors: Jan Cornelis and Stefania Perri
Sensors 2021, 21(18), 6070; https://doi.org/10.3390/s21186070
Received: 18 June 2021 / Revised: 3 September 2021 / Accepted: 7 September 2021 / Published: 10 September 2021
(This article belongs to the Section Intelligent Sensors)
Deep learning methods predicated on convolutional neural networks and graph neural networks have enabled significant improvement in node classification and prediction when applied to graph representation with learning node embedding to effectively represent the hierarchical properties of graphs. An interesting approach (DiffPool) utilises a differentiable graph pooling technique which learns ‘differentiable soft cluster assignment’ for nodes at each layer of a deep graph neural network with nodes mapped on sets of clusters. However, effective control of the learning process is difficult given the inherent complexity in an ‘end-to-end’ model with the potential for a large number parameters (including the potential for redundant parameters). In this paper, we propose an approach termed FPool, which is a development of the basic method adopted in DiffPool (where pooling is applied directly to node representations). Techniques designed to enhance data classification have been created and evaluated using a number of popular and publicly available sensor datasets. Experimental results for FPool demonstrate improved classification and prediction performance when compared to alternative methods considered. Moreover, FPool shows a significant reduction in the training time over the basic DiffPool framework. View Full-Text
Keywords: knowledge graphs; graph classification; graph neural networks; graph convolutional network; hierarchical graph pooling; FPool knowledge graphs; graph classification; graph neural networks; graph convolutional network; hierarchical graph pooling; FPool
Show Figures

Figure 1

MDPI and ACS Style

Pham, H.V.; Thanh, D.H.; Moore, P. Hierarchical Pooling in Graph Neural Networks to Enhance Classification Performance in Large Datasets. Sensors 2021, 21, 6070. https://doi.org/10.3390/s21186070

AMA Style

Pham HV, Thanh DH, Moore P. Hierarchical Pooling in Graph Neural Networks to Enhance Classification Performance in Large Datasets. Sensors. 2021; 21(18):6070. https://doi.org/10.3390/s21186070

Chicago/Turabian Style

Pham, Hai V., Dat H. Thanh, and Philip Moore. 2021. "Hierarchical Pooling in Graph Neural Networks to Enhance Classification Performance in Large Datasets" Sensors 21, no. 18: 6070. https://doi.org/10.3390/s21186070

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop