Engineer friends often ask me: Graph Deep Learning sounds great, but are there any big commercial success stories? Is it being deployed in practical applications? Besides the obvious ones–recommendation systems at Pinterest, Alibaba and Twitter–a slightly nuanced success story is the Transformer architecture, which has taken the NLP industry by storm. Through this post, I want to establish links between Graph Neural Networks (GNNs) and Transformers. I’ll talk about the intuitions behind model architectures in the NLP and GNN communities, make connections using equations and figures, and discuss how we could work together to drive progress.
J. Zhang, Y. Dong, Y. Wang, J. Tang, and M. Ding. Proceedings of the 28th International Joint Conference on Artificial Intelligence, page 4278–4284. AAAI Press, (Aug 10, 2019)
D. Yang, P. Rosso, B. Li, and P. Cudre-Mauroux. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, page 1162–1172. New York, NY, USA, Association for Computing Machinery, (2019)
P. Chapman, G. Stapleton, J. Howse, and I. Oliver. 2011 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC), page 87-94. (September 2011)
X. Wang, and M. Zhang. Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, page 23341--23362. PMLR, (17--23 Jul 2022)
J. Feng, Y. Chen, F. Li, A. Sarkar, and M. Zhang. Advances in Neural Information Processing Systems, 35, page 4776--4790. Curran Associates, Inc., (2022)