Graph Databases and Graph Neural Networks

PDF
Published: Dec 23, 2024
DOI: https://doi.org/10.26265/jiim.v9i2.39198
Stratos Tsolakidis
a:1:{s:5:"en_US";s:77:"University of West Attica Department of Informatics and Computer Engineering ";}
Anastasios Tsolakidis
Evangelia Triperina
Νikitas Karanikolas
Christos Skourlas
Abstract

Purpose - Nowadays, social networks, online media sharing and e-commerce platforms generate a vast amount of data, which, among other information, capture the interactions among the users. Storing, analyzing and exploiting the aforementioned information allow the exploration of hidden and unstructured patterns. 


Design/methodology/approach - The associations among the users during their visit in a platform construct a graph network which capture all the generated data. Graph Neural Networks are applied in these data models, to make suggestions based on their topology. In the presented research, Graph Databases and Graph Neural Networks are utilized for data exploration and analysis in graph databases networks.


Findings - In this study, we compare the use of graph databases with relational databases for large-scale databases and we present that the use of graph neural networks over graph databases can be used efficiently to apply machine learning tasks for those datasets.


Originality/value - Thus, in this paper, we present the benefits of applying graph neural networks and graph databases for data analysis in large-scale data from social networks. Also, we examine to the efficiency of using graph databases over relational databases for analyzing those networks.

Article Details
  • Section
  • Research Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Copyright Notice

Authors who publish with JIIM agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution Non-Commercial License that allows others to share the work with:
  2. An acknowledgment of the work's authorship and initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (preferably in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
References
Almabdy, S. (2018). Comparative analysis of relational and graph databases for social networks. In 2018 1st International Conference on Computer Applications & Information Security (ICCAIS) (pp. 1-4). IEEE. https://doi.org/10.1109/CAIS.2018.8441982
Kumar Kaliyar, R. (2015, May). Graph databases: A survey. In International Conference on Computing, Communication & Automation (pp. 785-790). IEEE. https://doi.org/10.1109/CCAA.2015.7148480
Bhattacharyya, A., & Chakravarty, D. (2020, January). Graph database: A survey. In 2020 International Conference on Computer, Electrical & Communication Engineering (ICCECE) (pp. 1-8). IEEE. https://doi.org/10.1109/ICCECE48148.2020.9223105
Tian, Y. (2023). The world of graph databases from an industry perspective. ACM SIGMOD Record, 51(4), 60-67. https://doi.org/10.1145/3582302.3582320
Xirogiannopoulos, K., & Deshpande, A. (2017, May). Extracting and analyzing hidden graphs from relational databases. In Proceedings of the 2017 ACM International Conference on Management of Data (pp. 897-912). https://doi.org/10.1145/3035918.3035949
Besta, M., Iff, P., Scheidl, F., Osawa, K., Dryden, N., Podstawski, M., Chen, T., & Hoefler, T. (2022, December). Neural graph databases. In Learning on Graphs Conference (pp. 31-1). PMLR.
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2008). The graph neural network model. IEEE transactions on neural networks, 20(1), 61-80. https://doi.org/10.1109/TNN.2008.2005605
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020). Graph neural networks: A review of methods and applications. AI open, 1, 57-81. https://doi.org/10.1016/j.aiopen.2021.01.001
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S.. (2020). A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1), 4-24. https://doi.org/10.1109/TNNLS.2020.2978386
Xu, K., Hu, W., Leskovec, J., & Jegelka, S. (2018). How Powerful are Graph Neural Networks?. In International Conference on Learning Representations.
Zhu, H., & Koniusz, P. (2021, May). Simple spectral graph convolution. In International conference on learning representations.
Behún, M. (2023). Graph neural networks and their application to social network analysis [Master’s thesis, Charles University]. Charles University Digital Depository.
Robinson, I., Webber, J., and Eifrem, E. (2015). Graph Databases: New Opportunities for Connected Data (2nd ed.). O’Reilly Media.
Sandell, J., Asplund, E., Ayele, W. Y., & Duneld, M. (2024). Performance Comparison Analysis of ArangoDB, MySQL, and Neo4j: An Experimental Study of Querying Connected Data. Hawaii International Conference on System Sciences 2024
McPherson, M., Smith-Lovin, L., & Cook, J. M. (2001). Birds of a feather: Homophily in social networks. Annual review of sociology, 27(1), 415-444. https://doi.org/10.1146/annurev.soc.27.1.415
Marsden, P. V., & Friedkin, N. E. (1993). Network studies of social influence. Sociological Methods & Research, 22(1), 127-151. https://doi.org/10.1177/0049124193022001006
Gao, C., Zheng, Y., Li, N., Li, Y., Qin, Y., Piao, J., Quan, Y., Chang, J., Jin, D., He, X. & Li, Y. (2023). A survey of graph neural networks for recommender systems: Challenges, methods, and directions. ACM Transactions on Recommender Systems, 1(1), 1-51. https://doi.org/10.1145/3568022
Sharma, K., Lee, Y. C., Nambi, S., Salian, A., Shah, S., Kim, S. W., & Kumar, S. (2024). A survey of graph neural networks for social recommender systems. ACM Computing Surveys, 56(10), 1-34. https://doi.org/10.1145/3661821
Jamali, M., & Ester, M. (2010). A matrix factorization technique with trust propagation for recommendation in social networks. In Proceedings of the fourth ACM conference on Recommender systems (pp. 135-142). https://doi.org/10.1145/1864708.1864736
Yang, B., Lei, Y., Liu, J., & Li, W. (2016). Social collaborative filtering by trust. IEEE transactions on pattern analysis and machine intelligence, 39(8), 1633-1647. https://doi.org/10.1109/TPAMI.2016.2605085
Deng, S., Huang, L., Xu, G., Wu, X., & Wu, Z. (2017). On deep learning for trust-aware recommendations in social networks. IEEE transactions on neural networks and learning systems, 28(5), 1164-1177. https://doi.org/10.1109/TNNLS.2016.2514368
Krishnan, A., Cheruvu, H., Tao, C., & Sundaram, H. (2019, November). A modular adversarial approach to social recommendation. In Proceedings of the 28th ACM international conference on information and knowledge management (pp. 1753-1762). https://doi.org/10.1145/3357384.3357898
Wu, S., Sun, F., Zhang, W., Xie, X., & Cui, B. (2022). Graph neural networks in recommender systems: a survey. ACM Computing Surveys, 55(5), 1-37. https://doi.org/10.1145/3535101
Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.
Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in neural information processing systems, 30.
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2018). Graph attention networks. In International Conference on Learning Representations.
Li, Y., Tarlow, D., Brockschmidt, M., & Zemel, R. (2016). Gated graph sequence neural networks. In International Conference on Learning Representations.
Feng, Y., You, H., Zhang, Z., Ji, R., & Gao, Y. (2019, July). Hypergraph neural networks. In Proceedings of the AAAI conference on artificial intelligence (Vol. 33, No. 01, pp. 3558-3565). https://doi.org/10.1609/aaai.v33i01.33013558.
Battaglia, P., Pascanu, R., Lai, M., & Jimenez Rezende, D. (2016). Interaction networks for learning about objects, relations and physics. Advances in neural information processing systems, 29.
Fout, A., Byrd, J., Shariat, B., & Ben-Hur, A. (2017). Protein interface prediction using graph convolutional networks. Advances in neural information processing systems, 30.