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.
N. Peng, H. Poon, C. Quirk, K. Toutanova, and W. Yih. ACL, (2017)cite arxiv:1708.03743Comment: Conditional accepted by TACL in December 2016; published in April 2017; presented at ACL in August 2017.
J. Leskovec, and C. Faloutsos. Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, page 631--636. ACM, (2006)