Abstract
Convolutional Neural Networks (ConvNets or CNNs) are that class of Neural Networks that have confirm very effective in areas such as classification and image recognition. Graph convolution neural network is that area of work that deals with the generalization of well-established neural models like convnets on structured datasets as there are numerous important problems that can be framed as learning from graph data. This paper focused to overcome one of the major weaknesses GCNN poses i.e. GCNN are Translational Invariant means these neural models are unable to identify the position of one object with respect to another. For example, the model will predict a car if it sees a bunch of random car parts like wheels, steering, headlights, and so on because all the key features are there. So, the main problem is to identify that the car parts are not in the correct position relative to another. We performed the experiments on two benchmark datasets, MNIST and smallNORB, and the accuracies obtained with our proposed models are comparably high. Thus the technique is able to preserve the spatial relationship among objects in the given structured dataset is the main motivation behind this paper.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Albawi, S., Mohammed, T.A., Al-Zawi, S.: Understanding of a convolutional neural network. In: 2017 International Conference on Engineering and Technology (ICET), pp. 1–6. IEEE (2017)
Henaff, M., Bruna, J., LeCun, Y.: Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163 (2015)
Hinton, G.E., Sabour, S., Frosst, N.: Matrix capsules with EM routing. In: International Conference on Learning Representations (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kulkarni, T.D., Whitney, W., Kohli, P., Tenenbaum, J.B.: Deep convolutional inverse graphics network. arXiv preprint arXiv:1503.03167 (2015)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
LeCun, Y., Huang, F.J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, p. II-104 (2004)
Mathieu, M., Henaff, M., LeCun, Y.: Fast training of convolutional networks through FFTs. In: 2nd International Conference on Learning Representations, ICLR 2014 (2014)
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. arXiv preprint arXiv:1710.09829 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Xiang, C., Zhang, L., Tang, Y., Zou, W., Xu, C.: MS-CapsNet: a novel multi-scale capsule network. IEEE Sig. Process. Lett. 25(12), 1850–1854 (2018)
Xinyi, Z., Chen, L.: Capsule graph neural network. In: International Conference on Learning Representations (2018)
Yang, M., Liu, Y., You, Z.: The Euclidean embedding learning based on convolutional neural network for stereo matching. Neurocomputing 267, 195–200 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yadav, R.K., Abhishek, Shukla, P., Tabassum, N., Tomar, R.S., Verma, S. (2021). Spatial Information Preservation in Graph Convolutional Neural Network. In: Tomar, R.S., et al. Communication, Networks and Computing. CNC 2020. Communications in Computer and Information Science, vol 1502. Springer, Singapore. https://doi.org/10.1007/978-981-16-8896-6_17
Download citation
DOI: https://doi.org/10.1007/978-981-16-8896-6_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8895-9
Online ISBN: 978-981-16-8896-6
eBook Packages: Computer ScienceComputer Science (R0)