Abstract
Given graphs as input, Graph Neural Networks (GNNs) support the inference of nodes, edges, attributes, or graph properties. Graph Rewriting investigates the rule-based manipulation of graphs to model complex graph transformations. We propose that, therefore, (i) graph rewriting subsumes GNNs and could serve as formal model to study and compare them, and (ii) the representation of GNNs as graph rewrite systems can help to design and analyse GNNs, their architectures and algorithms. Hence we propose Graph Rewriting Neural Networks (GReNN) as both novel semantic foundation and engineering discipline for GNNs. We develop a case study reminiscent of a Message Passing Neural Network realised as a Groove graph rewriting model and explore its incremental operation in response to dynamic updates.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Allamanis, M., Brockschmidt, M., Khademi, M.: Learning to represent programs with graphs. arXiv:1711.00740 [cs], May 2018. https://arxiv.org/abs/1711.00740
Anjum, A., Ikram, A., Hill, R., Antonopoulos, N., Liu, L., Sotiriadis, S.: Approaching the internet of things (IoT): a modelling, analysis and abstraction framework. Concurrency Comput.: Pract. Experience 27(8), 1966–1984 (2013)
Bronstein, M.: Using subgraphs for more expressive GNNs. Medium, December 2021. https://towardsdatascience.com/using-subgraphs-for-more-expressive-gnns-8d06418d5ab
Bronstein, M.: Beyond message passing: a physics-inspired paradigm for graph neural networks. Gradient (2022). https://thegradient.pub/graph-neural-networks-beyond-message-passing-and-weisfeiler-lehman
Brown, K., Patterson, E., Hanks, T., Fairbanks, J.P.: Computational category-theoretic rewriting. In: Behr, N., Strüber, D. (eds.) Graph Transformation - 15th International Conference, ICGT 2022, Held as Part of STAF 2022, Nantes, France, July 7–8, 2022, Proceedings. Lecture Notes in Computer Science, vol. 13349, pp. 155–172. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-09843-7_9
Duvenaud, D., et al.: Convolutional networks on graphs for learning molecular fingerprints. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems, December 2015, pp. 7–12 (2015). Montreal, Quebec, Canada, pp. 2224–2232 (2015). https://proceedings.neurips.cc/paper/2015/hash/f9be311e65d81a9ad8150a60844bb94c-Abstract.html
Eksombatchai, C., et al.: Pixie: a system for recommending 3+ billion items to 200+ million users in real-time. arXiv:1711.07601 [cs], November 2017. https://arxiv.org/abs/1711.07601
Galke, L., Vagliano, I., Scherp, A.: Incremental training of graph neural networks on temporal graphs under distribution shift. CoRR abs/2006.14422 (2020). https://arxiv.org/abs/2006.14422
Ghamarian, A.H., de Mol, M., Rensink, A., Zambon, E., Zimakova, M.: Modelling and analysis using GROOVE. Int. J. Softw. Tools Technol. Transf. 14(1), 15–40 (2012). https://doi.org/10.1007/s10009-011-0186-x
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. CoRR abs/1704.01212 (2017). http://arxiv.org/abs/1704.01212
Han, X., Jia, M., Chang, Y., Li, Y., Wu, S.: Directed message passing neural network (D-MPNN) with graph edge attention (GEA) for property prediction of biofuel-relevant species. Energy AI 10, 100201 (2022). https://www.sciencedirect.com/science/article/pii/S2666546822000477
Heckel, R., Taentzer, G.: Graph Transformation for Software Engineers. Springer International Publishing, Cham (2020). http://graph-transformation-for-software-engineers.org/
Hogan, A., et al.: Knowledge Graphs. No. 22 in Synthesis Lectures on Data, Semantics, and Knowledge. Morgan & Claypool (2021). https://kgbook.org/
Lample, G., Charton, F.: Deep learning for symbolic mathematics. arXiv:1912.01412 [cs], December 2019. https://arxiv.org/abs/1912.01412
Lange, O., Perez, L.: Traffic prediction with advanced graph neural networks, September 2020. https://www.deepmind.com. https://www.deepmind.com/blog/traffic-prediction-with-advanced-graph-neural-networks
Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.S.: Gated graph sequence neural networks. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2–4, 2016, Conference Track Proceedings (2016). http://arxiv.org/abs/1511.05493
Monti, F., Frasca, F., Eynard, D., Mannion, D., Bronstein, M.M.: Fake news detection on social media using geometric deep learning. arXiv:1902.06673 [cs, stat], February 2019. https://arxiv.org/abs/1902.06673
Sanchez-Gonzalez, A., Godwin, J., Pfaff, T., Ying, R., Leskovec, J., Battaglia, P.: Learning to simulate complex physics with graph networks, November 2020. https://proceedings.mlr.press/v119/sanchez-gonzalez20a.html
Sanchez-Lengeling, B., Reif, E., Pearce, A., Wiltschko, A.: A gentle introduction to graph neural networks. Distill 6(8), August 2021
Schad, J.: Graph powered machine learning: Part 1. ML Conference Berlin, October 2021. https://mlconference.ai/ml-summit/
Schütt, K.T., Arbabzadah, F., Chmiela, S., Müller, K.R., Tkatchenko, A.: Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8(1), January 2017. https://doi.org/10.1038%2Fncomms13890
Stokes, J.M., et al.: A deep learning approach to antibiotic discovery. Cell 180(4), 688–702.e13, February 2020. https://www.cell.com/cell/fulltext/S0092-8674(20)30102-1
Wang, Z., et al.: Heterogeneous relational message passing networks for molecular dynamics simulations. CoRR abs/2109.00711 (2021). https://arxiv.org/abs/2109.00711
Xu, L., He, Z.Y., Wang, K., Wang, C.D., Huang, S.Q.: Explicit message-passing heterogeneous graph neural network. IEEE Trans. Knowl. Data Eng., 1–13 (2022)
Zhou, J., et al.: Graph neural networks: a review of methods and applications. AI Open 1, 57–81 (2020). https://www.sciencedirect.com/science/article/pii/S2666651021000012
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Machowczyk, A., Heckel, R. (2023). Graph Rewriting for Graph Neural Networks. In: Fernández, M., Poskitt, C.M. (eds) Graph Transformation. ICGT 2023. Lecture Notes in Computer Science, vol 13961. Springer, Cham. https://doi.org/10.1007/978-3-031-36709-0_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-36709-0_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36708-3
Online ISBN: 978-3-031-36709-0
eBook Packages: Computer ScienceComputer Science (R0)