The site presents a hierarchical organization for Wikipedia articles with respect to their semantic similarity and provides search and navigation facilities over the hierarchy. The hierarchy is constructed as a recursive division of the English Wikipedia graph into dense subgraphs (graph communities) and can be considered as an extension to the Wikipedia category structure. Unlike Wikipedia categories that are primarily authored by humans, the community hierarchy is fully automatic, purely link-based and reflects the global link structure of Wikipedia.
Gephi is an open-source software for visualizing and analyzing large networks graphs. Gephi uses a 3D render engine to display graphs in real-time and speed up the exploration. Use Gephi to explore, analyse, spatialise, filter, cluterize, manipulate and export all types of graphs.
MSAGL is a .NET tool for graph layout and viewing. It was developed in Microsoft Research by Lev Nachmanson. MSAGL is built on the principle of the Sugiyama scheme; it produces so called layered, or hierarchical layouts. This kind of a layout naturally applies to graphs with some flow of information. The graph could represent a control flow graph of a program, a state machine, a C++ class hierarchy, etc.
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.
D. Liben-Nowell, and J. Kleinberg. CIKM '03: Proceedings of the twelfth international conference on Information and knowledge management, page 556--559. New York, NY, USA, ACM Press, (2003)
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.