Machine Learning on Graph-Structured Data

• Claudio D. T. Barros Laboratório Nacional de Computação Científica (LNCC) http://orcid.org/0000-0002-7216-4376
• Daniel N. R. da Silva Laboratório Nacional de Computação Científica (LNCC)
• Fabio A. M. Porto Laboratório Nacional de Computação Científica (LNCC)

DOI: https://doi.org/10.5753/sbbd_estendido.2021.18179

Resumo

Several real-world complex systems have graph-structured data, including social networks, biological networks, and knowledge graphs. A continuous increase in the quantity and quality of these graphs demands learning models to unlock the potential of this data and execute tasks, including node classification, graph classification, and link prediction. This tutorial presents machine learning on graphs, focusing on how representation learning - from traditional approaches (e.g., matrix factorization and random walks) to deep neural architectures - fosters carrying out those tasks. We also introduce representation learning over dynamic and knowledge graphs. Lastly, we discuss open problems, such as scalability and distributed network embedding systems.

Palavras-chave: Machine Learning, Graphs, Embeddings, Representation Learning

Referências

Alon, U. and Yahav, E. (2020). On the bottleneck of graph neural networks and its practical implications. arXiv preprint arXiv:2006.05205.

Barros, C. D., Mendonça, M. R., Vieira, A. B., and Ziviani, A. (2021). A survey on embedding dynamic graphs. arXiv preprint arXiv:2101.01229.

Bojchevski, A., Klicpera, J., Perozzi, B., Kapoor, A., Blais, M., Rózemberczki, B., Lukasik, M., and Günnemann, S. (2020). Scaling graph neural networks with approximate pagerank. In Proceedings of the 26th ACM SIGKDD International Conferenceon Knowledge Discovery & Data Mining, pages 2464–2473.

Cai, H., Zheng, V. W., and Chang, K. C.-C. (2018). A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE Transactions on Knowledgeand Data Engineering, 30(9):1616–1637.

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press.

Hamilton, W. L. (2020). Graph representation learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 14(3):1–159.

Mohri, M., Rostamizadeh, A., and Talwalkar, A. (2018). Foundations of Machine Learning. MIT Press.

Nickel, M., Murphy, K., Tresp, V., and Gabrilovich, E. (2015). A review of relational machine learning for knowledge graphs. Proceedings of the IEEE, 104(1):11–33.

Zhang, D., Huang, X., Liu, Z., Zhou, J., Hu, Z., Song, X., Ge, Z., Wang, L., Zhang,Z., and Qi, Y. (2020). Agl: A scalable system for industrial-purpose graph machine learning. Proc. VLDB Endow., 13(12):3125–3137.