TY  - CONF
AU  - Pau Riba
AU  - Andreas Fischer
AU  - Josep Llados
AU  - Alicia Fornes
A2  - ICPR
PY  - 2018//
TI  - Learning Graph Distances with Message Passing Neural Networks
BT  - 24th International Conference on Pattern Recognition
SP  - 2239
EP  - 2244
KW  - ★Best Paper Award★
N2  - 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.
L1  - http://refbase.cvc.uab.es/files/RFL2018.pdf
UR  - http://dx.doi.org/10.1109/ICPR.2018.8545310
N1  - DAG; 600.097; 603.057; 601.302; 600.121
ID  - Pau Riba2018
ER  -