Timezone: »

 
Oral
Graph Element Networks: adaptive, structured computation and memory
Ferran Alet · Adarsh Keshav Jeewajee · Maria Bauza Villalonga · Alberto Rodriguez · Tomas Lozano-Perez · Leslie Kaelbling

Wed Jun 12 02:40 PM -- 03:00 PM (PDT) @ Hall A

We explore the use of graph-structured neural-networks (GNNs) to model spatial processes in which there is no {\em a priori} graphical structure. Similar to {\em finite element analysis}, we assign nodes of a GNN to spatial locations and use a computational process defined on the graph to model the relationship between an initial function defined over a space and a resulting function. The encoding of inputs to node states, the decoding of node states to outputs, as well as the mappings defining the GNN are learned from a training set consisting of data from multiple function pairs. The locations of the nodes in space as well as their connectivity can be adjusted during the training process. This graph-based representational strategy allows the learned input-output relationship to generalize over the size and even topology of the underlying space. We demonstrate this method on a traditional PDE problem, a physical prediction problem from robotics, and a problem of learning to predict scene images from novel viewpoints.

Author Information

Ferran Alet (MIT)
Adarsh Keshav Jeewajee (Massachusetts Institute of Technology)
Maria Bauza Villalonga (MIT)
Alberto Rodriguez (MIT)
Tomas Lozano-Perez (MIT)
Leslie Kaelbling ((organization))

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors