Re:Graph-Powered Machine Learning at Google
by onetwo12 on Saturday October 08, 2016 @05:13AM
(#12666243)
I see this as a knn approach in which the distance is a function of the strength of the edge between the vertices.
In the retrofitting paper cited in the comments there is a process of smoothing, that is feeding back the message or information to update the states of the graph (example in the modern ai book). It doesn't seem anything new.
In the retrofitting paper cited in the comments there is a process of smoothing, that is feeding back the message or information to update the states of the graph (example in the modern ai book). It doesn't seem anything new.