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.
Q. Le, und T. Mikolov. Proceedings of the 31st International Conference on Machine Learning, Volume 32 von Proceedings of Machine Learning Research, Seite 1188--1196. Bejing, China, PMLR, (Juni 2014)
Y. Liu, A. Ganguly, und J. Dy. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Seite 3145–3153. New York, NY, USA, ACM, (2020)
Z. Zhang, S. Liu, M. Li, M. Zhou, und E. Chen. Proceedings of the 22nd Conference on Computational Natural Language Learning, CoNLL 2018, Brussels, Belgium, October 31 - November 1, 2018, Seite 190--199. Association for Computational Linguistics, (2018)
M. Valdenegro-Toro, O. Arriaga, und P. Plöger. 27th European Symposium on Artificial Neural Networks, ESANN 2019, Bruges, Belgium, April 24-26, 2019, (2019)
A. Kadra, M. Lindauer, F. Hutter, und J. Grabocka. Proceedings of the international conference on Neural Information Processing Systems (NeurIPS), (Dezember 2021)
M. Benjak, Y. Samayoa, und J. Ostermann. Proceedings of the 28th IEEE International Conference on Image Processing (ICIP), (September 2021)accepted for publication.