/* ---- Google Analytics Code Below */

Sunday, July 07, 2019

Innovations in Graph Representation Learning

From the Google AI Blog.  Good introduction to semantic networks.  And some technical information about where they are experimenting.   To model something complex, you first need to have a basic representation, a graph is a good place to start.   In particular because it can be used to explain the complexity to non technicals.

Innovations in Graph Representation Learning
Tuesday, June 25, 2019
Posted by Alessandro Epasto, Senior Research Scientist and Bryan Perozzi, Senior Research Scientist, Graph Mining Team

Relational data representing relationships between entities is ubiquitous on the Web (e.g., online social networks) and in the physical world (e.g., in protein interaction networks). Such data can be represented as a graph with nodes (e.g., users, proteins), and edges connecting them (e.g., friendship relations, protein interactions). Given the widespread prevalence of graphs, graph analysis plays a fundamental role in machine learning, with applications in clustering, link prediction, privacy, and others. To apply machine learning methods to graphs (e.g., predicting new friendships, or discovering unknown protein interactions) one needs to learn a representation of the graph that is amenable to be used in ML algorithms.

However, graphs are inherently combinatorial structures made of discrete parts like nodes and edges, while many common ML methods, like neural networks, favor continuous structures, in particular vector representations. Vector representations are particularly important in neural networks, as they can be directly used as input layers. To get around the difficulties in using discrete graph representations in ML, graph embedding methods learn a continuous vector space for the graph, assigning each node (and/or edge) in the graph to a specific position in a vector space. A popular approach in this area is that of random-walk-based representation learning, as introduced in DeepWalk.   .... " (more useful content follows at the link)

No comments: