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.
A. Singla, and I. Weber. WSDM '09: Proceedings of the Second ACM International Conference on Web Search and Data Mining, page 252--261. New York, NY, USA, ACM, (2009)
P. Symeonidis, A. Nanopoulos, and Y. Manolopoulos. RecSys '08: Proceedings of the 2008 ACM conference on Recommender systems, page 43--50. New York, NY, USA, ACM, (2008)
I. Dhillon. KDD '01: Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, page 269--274. New York, NY, USA, ACM Press, (2001)
T. Hu, H. Xiong, W. Zhou, S. Sung, and H. Luo. SIGIR '08: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, page 871--872. New York, NY, USA, ACM, (2008)
C. Karande, K. Chellapilla, and R. Andersen. WSDM '09: Proceedings of the Second ACM International Conference on Web Search and Data Mining, page 272--281. New York, NY, USA, ACM, (2009)