Learning Structural Loss Parameters on Graph Embedding Applied on Symbolic Graphs

Research output: Book/ReportProceedingResearchpeer-review

1 Citation (Scopus)


We propose an amelioration of proposed Graph Embedding (GEM) method in previous work that takes advantages of structural pattern representation and the structured distortion. it models an Attributed Graph (AG) as a Probabilistic Graphical Model (PGM). Then, it learns the parameters of this PGM presented by a vector, as new signature of AG in a lower dimensional vectorial space. We focus to adapt the structured learning algorithm via 1-slack formulation with a suitable risk function, called Graph Edit Distance (GED). It defines the dissimilarity of the ground truth and predicted graph labels. It determines by the error tolerant graph matching using bipartite graph matching algorithm. We apply Structured Support Vector Machines (SSVM) to process classification task. During our experiments, we got our results on the GREC dataset.

Original languageEnglish
Number of pages2
Publication statusPublished - 25 Jan 2018

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN (Print)1520-5363


  • Attributed Graph
  • Graph Embedding
  • Probabilistic Graphical Model
  • Structural dissimilarity distance
  • Structured Support Vector Machines


Dive into the research topics of 'Learning Structural Loss Parameters on Graph Embedding Applied on Symbolic Graphs'. Together they form a unique fingerprint.

Cite this