Deep Neural Networks for Graph Data Processing
| Thesis title in Czech: | Deep Neural Networks for Graph Data Processing |
|---|---|
| Thesis title in English: | Deep Neural Networks for Graph Data Processing |
| Key words: | hluboké neuronové sítě|grafové neuronové sítě|grafové konvoluční sítě|grafové autoenkodéry|grafové neuronové sítě s pozorností|planární grafy |
| English key words: | deep neural networks|graph neural networks|graph convolutional networks|graph autoencoders|graph attention networks|planar graphs|graph isomorphism |
| Academic year of topic announcement: | 2023/2024 |
| Thesis type: | Bachelor's thesis |
| Thesis language: | angličtina |
| 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: | 17.06.2024 |
| Date of assignment: | 17.06.2024 |
| Confirmed by Study dept. on: | 13.07.2024 |
| Date and time of defence: | 06.09.2024 09:00 |
| Date of electronic submission: | 15.07.2024 |
| Date of submission of printed version: | 15.07.2024 |
| Date of proceeded defence: | 06.09.2024 |
| Opponents: | Mgr. Vladan Majerech, Dr. |
| Guidelines |
| The student shall review the following topics in his bachelor's thesis:
- neural network architectures applicable to deep learning – convolutional neural networks (CNN), recurrent neural networks of the long short-term memory (LSTM) type, and transformers, among others, - graph neural networks and their variants, in particular, the models of graph convolutional networks (GCN), graph autoencoders (GAE), and graph attention networks (GAT). He shall propose a suitable strategy to reliably process real-world graph data (e.g., from the areas of chemistry or biology). Preferably, the processed data shall have a planar graph form. Furthermore, the student shall develop a suitable representation of the involved data and implement the models. Evaluating the results and the gained experience will be vital to the thesis. |
| References |
| 1. Some of the textbooks available for the chosen area of research, e.g.:
- C. C. Agarwal: Neural Networks and Deep Learning, Springer, (2018). - C. M. Bishop, H. Bishop: Deep Learning, Springer, (2024). - W. L. Hamilton: Graph Representation Learning, Springer, (2022). - L. Wu, P. Cui, J. Pei, L. Zhao: Graph Neural Networks: Foundations, Frontiers, and Applications, Springer, (2022). 2. Journal papers and other publications: - R. Dimitrov, Z. Zhao, R. Abboud, and I. I. Ceylan: PlanE: Representation Learning over Planar Graphs, in: Proc. of NeurIPS 2023, (2023), 27 p. - W. Gao, S. P. Mahajan, J. Sulam, and J. J. Gray: Deep Learning in Protein Structure Modeling and Design, in: Patterns, Vol. 1, No. 9, (2020), 23 p. - D. Grattarola and C. Alippi: Graph Neural Networks in TensorFlow and Keras with Spektral, in: IEEE Computational Intelligence Magazine, Vol. 16, No. 1, (2021), pp. 99-106. - Ch. Morris, N. M. Kriege, F. Bause, K. Kersting, P. Mutzel, and M. Neumann: TUDataset: A collection of benchmark datasets for learning with graphs, in: Proc. of ICML 2020 - workshop "Graph Representation Learning and Beyond," (2020), 11 p. - F. Scarselli et al.: The Graph Neural Network Model, in: IEEE Transactions on Neural Networks, Vol. 20, No.1, 2009, pp. 61-80. - 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. - 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, e.g.: IEEE Transactions on Neural Networks and Learning Systems, Neural Networks, Neurocomputing, etc. |