Overview of Graph Neural Networks
Speaker: David Blanco Mulero
Email: david.blancomulero@aalto.fi
Robotics Seminar Series. Next Session – 23rd April 2021, 15:00-16:00, via zoom. Link to event: https://aalto.zoom.us/j/62124942899
Abstract: Graphs are a powerful representation that can describe relations in many fields such as chemistry, physics or social science. In recent years, Graph Neural Networks (GNNs) have become a hot topic in machine learning.
In this seminar, I will give an overview of Graph Neural Networks: what they are, how can we use them, and some of their applications.
References:
- Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., … & Sun, M. (2020). Graph neural networks: A review of methods and applications. AI Open, 1, 57-81.
- Zhang, Z., Cui, P., & Zhu, W. (2020). Deep learning on graphs: A survey. IEEE Transactions on Knowledge and Data Engineering.
- Sanchez-Gonzalez, A., Heess, N., Springenberg, J. T., Merel, J., Riedmiller, M., Hadsell, R., & Battaglia, P. (2018, July). Graph networks as learnable physics engines for inference and control. In International Conference on Machine Learning (pp. 4470-4479). PMLR.
- Battaglia, P. W., Hamrick, J. B., Bapst, V., Sanchez-Gonzalez, A., Zambaldi, V., Malinowski, M., … & Pascanu, R. (2018). Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261.