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.
X. Hu, W. Liu, J. Bian, и J. Pei. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, стр. 1521--1531. (2020)
Z. Fernando, J. Singh, и A. Anand. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, стр. 1005--1008. (2019)
J. Rotsztejn, N. Hollenstein, и C. Zhang. (2018)cite arxiv:1804.02042Comment: Accepted to SemEval 2018 (12th International Workshop on Semantic Evaluation).
R. Srivastava, K. Greff, и J. Schmidhuber. (2015)cite arxiv:1505.00387Comment: 6 pages, 2 figures. Presented at ICML 2015 Deep Learning workshop. Full paper is at arXiv:1507.06228.
S. Bowman, C. Manning, и C. Potts. (2015)cite arxiv:1506.04834Comment: To appear in the proceedings of the 2015 NIPS Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches.
