PT Unknown
AU Pau Riba
   Andreas Fischer
   Josep Llados
   Alicia Fornes
TI Learning Graph Distances with Message Passing Neural Networks
BT 24th International Conference on Pattern Recognition
PY 2018
BP 2239
EP 2244
DI 10.1109/ICPR.2018.8545310
DE ★Best Paper Award★
AB Graph  representations  have  been  widely  used  in pattern   recognition   thanks   to   their   powerful   representation formalism and rich theoretical background. A number of error-tolerant graph matching algorithms such as graph edit distance have   been   proposed   for   computing   a   distance   between   two labelled   graphs.   However,   they   typically   suffer   from   a   highcomputational   complexity,   which   makes   it   difficult   to   applythese  matching  algorithms  in  a  real  scenario.  In  this  paper, we  propose  an  efficient  graph  distance  based  on  the  emerging field of geometric deep learning. Our method employs a message passing neural network to capture the graph structure and learns a  metric  with  a  siamese  network  approach.  The  performance of  the  proposed  graph  distance  is  validated  in  two  application cases,  graph  classification  and  graph  retrieval  of  handwritten words, and shows a promising performance when compared with(approximate)  graph  edit  distance  benchmarks.
ER