Relational data represent relationships between entities anywhere on the web (e.g. online social networks) or in the physical world (e.g. structure of the protein).
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.
K. Bollacker, C. Evans, P. Paritosh, T. Sturge, and J. Taylor. SIGMOD '08: Proceedings of the 2008 ACM SIGMOD international conference on Management of data, page 1247--1250. New York, NY, USA, ACM, (2008)
X. Xu, N. Yuruk, Z. Feng, and T. Schweiger. KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining, page 824--833. New York, NY, USA, ACM, (2007)
C. Ding, X. He, and H. Zha. KDD '01: Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, page 275--280. New York, NY, USA, ACM, (2001)
M. Toyoda, and M. Kitsuregawa. HYPERTEXT '05: Proceedings of the sixteenth ACM conference on Hypertext and hypermedia, page 151--160. New York, NY, USA, ACM, (2005)
D. Cai, Z. Shao, X. He, X. Yan, and J. Han. LinkKDD '05: Proceedings of the 3rd international workshop on Link discovery, page 58--65. New York, NY, USA, ACM, (2005)
Y. Jo, C. Lagoze, and C. Giles. KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining, page 370--379. New York, NY, USA, ACM, (2007)
H. Ino, M. Kudo, and A. Nakamura. WWW '05: Proceedings of the 14th international conference on World Wide Web, page 661--669. New York, NY, USA, ACM, (2005)
G. Flake, S. Lawrence, and C. Giles. KDD '00: Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, page 150--160. New York, NY, USA, ACM, (2000)