Graph neural networks are intimately related to partial differential equations governing information diffusion on graphs. Thinking of GNNs as PDEs leads to a new broad class of graph ML methods.
M. Ryabinin, S. Popov, L. Prokhorenkova, and E. Voita. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), page 7317--7331. Online, Association for Computational Linguistics, (November 2020)
N. Shao, Y. Cui, T. Liu, S. Wang, and G. Hu. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), page 7187--7192. Online, Association for Computational Linguistics, (November 2020)
M. Peters, M. Neumann, R. Logan, R. Schwartz, V. Joshi, S. Singh, and N. Smith. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), page 43--54. Hong Kong, China, Association for Computational Linguistics, (November 2019)
G. Lee, S. Kang, and J. Whang. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, (July 2019)
A. Dargahi Nobari, N. Reshadatmand, and M. Neshati. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, page 2035–2038. New York, NY, USA, Association for Computing Machinery, (2017)