Abstract
In this paper, both considering inter-instance relations and inter-label corre-lations simultaneously, a kernel Gaussian neural network sparse multi-label learning (GNN-SML) is proposed. More specifically, latent representation for sparse multi-label instance sets is constructed, both involving inter-instance and inter-label relations. The attacking problem is that instance features or label sets are too sparse to be extracted effectively hidden representation. Through both extracting inter-instance relations and inter-label correlations, it makes the learning latent representation more comprehensive, complete and accurate. At the same time, to grasp the uncertainty underlying in multi-label data, Gaussian process is introduced to denote the real underlying distribution of multi-label dataset. Additionally, this paper also incorporates self-attention mechanism to adjust its weight in the calculation of contributions of different features for the final prediction results. Finally, the effectiveness of the GNN-SML is validated on the sparse multi-label datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Read, J., Pfahringer, B., Holmes, G., Frank, E.: Classifier chains for multi-label classification. In: Proceedings of the ECML PKDD 2009: Machine Learning and Knowledge Discovery in Databases, pp. 254–269 (2009)
Leordeanu, M.: Unsupervised Learning in Space and Time. ACVPR, Springer, Cham (2020). https://doi.org/10.1007/978-3-030-42128-1
Zhang, C.-Y., Hu, J., Yang, L., Chen, C.L.P., Yao, Z.: Graph de-convolutional networks. Inf. Sci. 518, 330–340 (2020)
Kejani, M.T., Dornaika, F., Talebi, H.: Graph Convolution Networks with manifold regularization for semi-supervised learning. Neural Networks 127, 160–167 (2020)
Zhou, J., Cui, G., Zhang, Z., Yang, C., Liu, Z., Sun, M.: Graph Neural Networks: A Review of Methods and Applications, CoRR abs/1812.08434 2018
Wang, Y., Yuan, Y., Ma, Y., Wang, G.: Time-dependent graphs: definitions, applications, and algorithms. Data Sci. Eng. 4(4), 352–366 (2019)
Pennec, X., Fillard, P., Ayache, N.: A Riemannian framework for tensor computing. Int. J. Comput. Vis. 66(1), 41–66 (2006)
Caseiro, R., Martins, P., Henriques, J.F., Batista, J.P.: A nonparametric Riemannian framework on tensor field with application to foreground segmentation. Pattern Recognit. 45(11), 3997–4017 (2012)
Laforgue, P., Clémençon, S., d’Alché-Buc, F.: Autoencoding any data through kernel autoencoders. In: The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), 1061–1069 (2019)
Xie, T., Wang, B., Kuo, C.C.J.: GraphHop, “An Enhanced Label Propagation Method for Node Classification," arXiv preprint arXiv:2101.02326 (2021)
Acknowledgement
This work was supported by the Science Foundation of China University of Petroleum, Beijing (No. 2462020YXZZ023).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lian, Sm., Liu, Jw. (2021). Abstracting Inter-instance Relations and Inter-label Correlation Simultaneously for Sparse Multi-label. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1516. Springer, Cham. https://doi.org/10.1007/978-3-030-92307-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-92307-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92306-8
Online ISBN: 978-3-030-92307-5
eBook Packages: Computer ScienceComputer Science (R0)