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.
A. Traud, P. Mucha, and M. Porter. (2011)cite arxiv:1102.2166
Comment: 82 pages (including many pages of tables), 8 multi-part figures,
"Facebook100" data used in this paper is publicly available at
http://people.maths.ox.ac.uk/~porterm/data/facebook100.zip.
C. Schmitz, A. Hotho, R. Jäschke, and G. Stumme. Data Science and Classification. Proceedings of the 10th IFCS Conf., page 261--270. Heidelberg, Springer, (July 2006)
B. Berendt, A. Hotho, and G. Stumme. Web Semantics: Science, Services and Agents on the World Wide Web, 8 (2-3):
95 - 96(2010)Bridging the Gap--Data Mining and Social Network Analysis for Integrating Semantic Web and Web 2.0; The Future of Knowledge Dissemination: The Elsevier Grand Challenge for the Life Sciences.
C. Schmitz, A. Hotho, R. Jäschke, and G. Stumme. Data Science and Classification (Proc. IFCS 2006 Conference), page 261-270. Berlin/Heidelberg, Springer, (July 2006)Ljubljana.
S. Maslov, and S. Redner. (2009)cite arxiv:0901.2640
Comment: 3 pages, 1 figure, invited comment for the Journal of Neuroscience.
The arxiv version is microscopically different from the published version.