Shift Aggregate Extract Networks
We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested part-of-part relations. Unlike recursive neural networks, which unroll a template on input...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2018-04-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/article/10.3389/frobt.2018.00042/full |