Transcription of Learning Convolutional Neural Networks for Graphs
{{id}} {{{paragraph}}}
Example: bankruptcy
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsMathias Labs Europe, Heidelberg, GermanyAbstractNumerous important problems can be framed aslearning from graph data. We propose a frame-work for Learning Convolutional Neural networksfor arbitrary Graphs . These Graphs may be undi-rected, directed, and with both discrete and con-tinuous node and edge attributes. Analogous toimage-based Convolutional Networks that oper-ate on locally connected regions of the input, wepresent a general approach to extracting locallyconnected regions from Graphs . Using estab-lished benchmark data sets, we demonstrate thatthe learned feature representations are competi-tive with state of the art graph kernels and thattheir computation is highly IntroductionWith this paper we aim to bring Convolutional Neural net-works to bear on a large class of graph -based Learning prob-lems.
neighborhood graphs as the CNN’s receptive fields. Figure2illustrates the PATCHY-SAN architecture which has several advantages over existing approaches: First, it is highly efficient, naively parallelizable, and applicable to large graphs. Second, for a number of applications, rang-ing from computational biology to social network analysis,
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: