Abstract
Cluster-GCN is one of the effective methods for studying the scalability of Graph Neural Networks. The idea of this approach is to use METIS community detection algorithm to split the graph into several sub-graphs, or communities that are small enough to fit into a common Graphics Processing Unit. However, METIS algorithm still has some limitations. Therefore, this research aims to improve the performance of cluster-GCN by changing the community detection algorithm, specifically by using Leiden algorithm as an alternative. Originally, Leiden algorithm is claimed to be powerful in identifying communities in networks. Nevertheless, the common feature of community detection algorithms makes nodes in the same community tend to be similar. For that reason, this research also proposes to add constraints such as minimum/maximum community size and overlapping communities to increase community diversity. By combining the above approaches with a careful analysis of protein data, our experiments on a single 8 GB GPU show that the performance of Cluster-GCN on the ogbn-proteins dataset could be improved by a 0.98% ROC-AUC score.
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
Szklarczyk, D., et al.: STRING v11: protein–protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets. Nucleic Acids Res. 47(D1), D607–D613 (2019)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv:1609.02907 (2016)
Chiang, W.-L., Liu, X., Si, S., Li, Y., Bengio, S., Hsieh, C.-J.: Cluster-GCN: an efficient algorithm for training deep and large graph convolutional networks. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 257–266 (2019)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, 30 (2017)
Chen, J., Ma, T., Xiao, C.: FastGCN: fast learning with graph convolutional networks via importance sampling. arXiv:1801.10247 (2018)
Chen, J., Zhu, J., Song, L.: Stochastic training of graph convolutional networks with variance reduction. arXiv:1710.10568 (2017)
Karypis, G., Kumar, V.: A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J. Sci. Comput. 20(1), 359–392 (1998)
Shiokawa, H., Onizuka, M.: Scalable graph clustering and its applications. In: Alhajj, R., Rokne, J. (eds.) Encyclopedia of Social Network Analysis and Mining, pp. 2290–2299. Springer, New York (2018). https://doi.org/10.1007/978-1-4939-7131-2_110185
Newman, M.E.J., Girvan, M.: Finding and evaluating community structure in networks. Phys. Rev. E 69(2), 026113 (2004)
Blondel, V.D., Guillaume, J.-L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. J. Stat. Mech. Theory Exp. 2008(10), P10008 (2008)
Traag, V.A., Waltman, L., Van Eck, N.J.: From Louvain to Leiden: guaranteeing well-connected communities. Sci. Rep. 9(1), 5233 (2019)
Liu, Y., Shah, N., Koutra, D.: An empirical comparison of the summarization power of graph clustering methods. arXiv:1511.06820 (2015)
Xu, H., Lou, D., Carin, L.: Scalable gromov-wasserstein learning for graph partitioning and matching. In: Advances in Neural Information Processing Systems, 32 (2019)
Li, G., Xiong, C., Thabet, A., Ghanem, B.: Deepergcn: All you need to train deeper gcns. arXiv:2006.07739 (2020)
Liu, W., Tang, Z., Wang, L., Li, M.: DCBGCN: an algorithm with high memory and computational efficiency for training deep graph convolutional network. In: Proceedings of the 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), pp. 16–21. IEEE (2020)
Luo, M., et al.: A novel high-order cluster-GCN-based approach for service recommendation. In: Xu, C., Xia, Y., Zhang, Y., Zhang, LJ. (eds.) ICWS 2021. LNCS, vol. 12994, pp. 32–45. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-96140-4_3
Li, G., Muller, M., Ghanem, B., Koltun, V.: Training graph neural networks with 1000 layers. In: International Conference on Machine Learning, pp. 6437–6449. PMLR (2021)
Xion, C.: Deep GCNs with random partition and generalized aggregator. Ph.D thesis. https://repository.kaust.edu.sa/bitstream/handle/10754/666216/ChenxinXiong_Masters_Thesis.pdf. Accessed 10 Feb 2023
Hu, W., et al.: Open graph benchmark: datasets for machine learning on graphs. Adv. Neural. Inf. Process. Syst. 33, 22118–22133 (2020)
Fey, M., Lenssen, J.E.: Fast graph representation learning with PyTorch geometric. arXiv:1903.02428 (2019)
Hung, P.D., Kien, N.N.: SSD-Mobilenet implementation for classifying fish species. In: Vasant, P., Zelinka, I., Weber, GW. (eds.) ICO 2019. AISC, vol. 1072, pp. 399–408. Springer, Cham. https://doi.org/10.1007/978-3-030-33585-4_40
Hung, P.D., Su, N.T., Diep, V.T.: Surface classification of damaged concrete using deep convolutional neural network. Pattern Recognit. Image Anal. 29, 676–687 (2019)
Hung, P.D., Su, N.T.: Unsafe construction behavior classification using deep convolutional neural network. Pattern Recognit. Image Anal. 31, 271–284 (2021)
Duy, L.D., Hung, P.D.: Adaptive graph attention network in person re-identification. Pattern Recognit. Image Anal. 32, 384–392 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Phuoc, N.B., Trang, D.T., Hung, P.D. (2023). A Cluster-Constrained Graph Convolutional Network for Protein-Protein Association Networks. In: Nguyen, N.T., et al. Intelligent Information and Database Systems. ACIIDS 2023. Lecture Notes in Computer Science(), vol 13996. Springer, Singapore. https://doi.org/10.1007/978-981-99-5837-5_14
Download citation
DOI: https://doi.org/10.1007/978-981-99-5837-5_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-5836-8
Online ISBN: 978-981-99-5837-5
eBook Packages: Computer ScienceComputer Science (R0)