✳flâneur — a map of the web's best reading

Graph Convolutional Networks | Thomas Kipf | Google DeepMind

tkipf.github.io · 2,558 words · saved by 1 readers

Many important real-world datasets come in the form of graphs or networks: social networks, knowledge graphs, protein-interaction networks, the World Wide Web, etc. (just to name a few). Yet, until recently, very little attention has been devoted to the generalization of neural...

Graph Convolutional Networks | Thomas Kipf | Google DeepMind Multi-layer Graph Convolutional Network (GCN) with first-order filters. Tweet 0 Share Overview Many important real-world datasets come in the form of graphs or networks: social networks, knowledge graphs, protein-interaction networks, the World Wide Web, etc. (just to name a few). Yet, until recently, very little attention has been devoted to the generalization of neural network models to such structured datasets. In the last couple of years, a number of papers re-visited this problem of generalizing neural networks to work on arbitr

Explore this link on the map →

saved by

related reading