消息传递框架再看

这部分内容有帮助吗？

参考文献

Relational Inductive Biases, Deep Learning, and Graph Networks, Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Caglar Gulcehre, Francis Song, Andrew Ballard, Justin Gilmer, George Dahl, Ashish Vaswani, Kelsey Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matt Botvinick, Oriol Vinyals, Yujia Li, Razvan Pascanu, Thomas P. Lillicrap, 2018 arXiv preprint arXiv:1806.01261 DOI: 10.48550/arXiv.1806.01261 - 此论文定义了统一的“图网络”框架，涵盖了消息传递机制并形式化了其组成部分。
How Powerful are Graph Neural Networks?, Keyulu Xu, Weihua Hu, Jure Leskovec, Yoshua Bengio, 2019 International Conference on Learning Representations (ICLR) DOI: 10.48550/arXiv.1810.00826 - 介绍了图同构网络（GIN），并正式将GNN的表达能力与1-Weisfeiler-Lehman测试关联起来。
Weisfeiler and Lehman Go Neural: Higher-order Graph Neural Networks, Christopher Morris, Martin Ritzert, Matthias Fey, Stefan Faber, Hongzhi Wen, William Hamilton, Laurent Schonsberg, Michiharu Akimoto, Martin Gütlein, Daniel Kuehn, Karsten Borgwardt, 2019 Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33 (American Association for Artificial Intelligence (AAAI)) DOI: 10.1609/aaai.v33i01.33013990 - 提供了一个理论框架，用于分析GNN在Weisfeiler-Lehman测试方面的表达能力，包括高阶变体。