Scalable graph neural networks for social network processing

• Thesis title in Czech: Scalable graph neural networks for social network processing
• Thesis title in English: Scalable graph neural networks for social network processing
• Key words: deep neural networks|graph neural networks|knowledge representation|socil networks|scalability
• English key words: deep neural networks|graph neural networks|knowledge representation|social networks|scalability
• Academic year of topic announcement: 2023/2024
• Thesis type: diploma thesis
• Department: Department of Theoretical Computer Science and Mathematical Logic (32-KTIML)
• Supervisor: doc. RNDr. Iveta Mrázová, CSc.
• Author: hidden - assigned and confirmed by the Study Dept.
• Date of registration: 10.12.2023
• Date of assignment: 11.12.2023
• Confirmed by Study dept. on: 12.12.2023

Guidelines

The student shall review the following topics in his diploma thesis:

- overview of the main principles underlying the graph neural network model (GNN), their training and variants, such as recurrent graph neural networks, convolutional graph neural networks, and graph autoencoders,
- exploration of the models´ scalability properties, in particular when considering their depth, node sampling or clustering, and graph heterogeneity (involving the presence of different types of nodes and edges),
- recapitulation of the paradigms and methods fundamental to social network data processing (e.g., identification of influential individuals and community detection),

The student will focus on some of these topics in more detail. Further, he will propose a suitable strategy applicable to the processing of large-scale social network data (e.g., from the area of economics) and will implement the models. Evaluating the obtained results and the gained experience shall form an essential part of the thesis.

References

1. Some of the textbooks available for the chosen area of research, e.g.:
- Ch. C. Aggarwal (Ed.): Social Network Data Analytics, Springer, (2011).
- A.-L. Barabási: Network Science, Cambridge University Press, (2016). http://networksciencebook.com/
- I. Goodfellow, Y. Bengio, A. Courville: Deep Learning, The MIT Press, (2016).
- L. Wu, P. Cui, J. Pei, L. Zhao: Graph Neural Networks: Foundations, Frontiers, and Applications, Springer, (2022).

2. Journal papers and other publications:
- J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun: Spectral Networks and Deep Locally Connected Networks on Graphs, in: Proc. of ICLR, (2014), 14 p. http://arxiv.org/abs/1312.6203.
- M. Defferrard, X. Bresson, P. Vandergheynst: Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering, in: Proc. of NIPS, (2016), 9 p. https://arxiv.org/pdf/1606.09375.
- W. L. Hamilton, R. Ying, and J. Leskovec: Inductive Representation Learning on Large Graphs, in: Proc. on NIPS, (2017), 11 p. https://arxiv.org/abs/1706.02216.
-K. He, X. Zhang, S. Ren, and J. Sun: Deep residual learning for image recognition, in: Proc. of CVPR, (2016), pp. 770-778.
- W. Hu, M. Fey, H. Ren, M. Nakata, Y. Dong, and J. Leskovec: Ogb-lsc: A large-scale challenge for machine learning on graphs, arXiv preprint, arXiv:2103.09430, (2021).
- L. Laugier, A. Wang, Ch.-S. Foo, T. Guenais, and V. Chandrasekhar: Encoding Knowledge Graph with Graph CNN for Question Answering, in: Proc. of ICLR, (2019), 5 p.
- Q. Li, Z. Han, and X.-M. Wu: Deeper insights into graph convolutional networks for semi-supervised learning, in: Proc. of AAAI, (2018), 8 p.
- G. Li, M. Muller, B. Ghanem, and V. Koltun: Training Graph Neural Networks with 1000 Layers, in: Proc. of PMLR 139, (2021), 13 p.
- Z. Liu et al.: GeniePath: Graph neural networks with adaptive receptive paths, in: Proc. of AAAI, (2019), pp. 4424-4431.
- M. Weber, G. Domeniconi, J. Chen, D. K. I. Weidele, C. Bellei, T. Robinson, and Ch. E. Leiserson: Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics, Tutorial in the Anomaly Detection in Finance Workshop at the 25th SIGKDD Conference on Knowledge Discovery and Data Mining, (2019), 7 p. https://arxiv.org/abs/1908.02591.
- Z. Wu, S. Pan, F.Chen, G. Long, Ch. Zhang, and P. S. Yu: A Comprehensive Survey on Graph Neural Networks, in: IEEE Transactions on Neural Networks and Learning Systems, Vol. 32, No. 1, (2021), pp. 4-24.
- K. Xu, W. Hu, j. Leskovec, and S. Jegelka: How powerful are graph neural networks, in: Proc. of ICLR, (2019), 17 p.
- Z. Ying, j. You, C. Morris, X. Ren, W. Hamilton, and J. Leskovec: Hierarchical graph representation learning with differentiable pooling, in: Proc. of NeurIPS, (2018), pp. 4801-4811.
- J. Zhou, G. Cui, S. Hu, Z. Zhang, Ch. Yang, Z. Liu, L. Wang, Ch. Li, and M. Sun: Graph Neural Networks: A Review of Methods and Applications, in: AI Open 1, (2020), pp. 57-81.

3. Relevant articles from leading academic journals:
Neurocomputing, Neural Networks, IEEE Transactions on Neural Networks and Learning Systems, etc.