Combinatorial learning of graph edit distance via dynamic embedding
Abstract Graph Edit Distance (GED) is a popular similarity measurement for pairwise graphs
and it also refers to the recovery of the edit path from the source graph to the target graph …
and it also refers to the recovery of the edit path from the source graph to the target graph …
Comparing heuristics for graph edit distance computation
Because of its flexibility, intuitiveness, and expressivity, the graph edit distance (GED) is one
of the most widely used distance measures for labeled graphs. Since exactly computing …
of the most widely used distance measures for labeled graphs. Since exactly computing …
Learning graph distances with message passing neural networks
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 …
representation formalism and rich theoretical background. A number of error-tolerant graph …
Graph neural networks using local descriptions in attributed graphs: an application to symbol recognition and hand written character recognition
Graph-based methods have been widely used by the document image analysis and
recognition community, as the different objects and the content in document images is best …
recognition community, as the different objects and the content in document images is best …
On the unification of the graph edit distance and graph matching problems
R Raveaux - Pattern Recognition Letters, 2021 - Elsevier
Error-tolerant graph matching gathers an important family of problems. These problems aim
at finding correspondences between two graphs while integrating an error model. In the …
at finding correspondences between two graphs while integrating an error model. In the …
Additive angular margin loss in deep graph neural network classifier for learning graph edit distance
The recent success of graph neural networks (GNNs) in the area of pattern recognition (PR)
has increased the interest of researchers to use these frameworks in non-euclidean …
has increased the interest of researchers to use these frameworks in non-euclidean …
Approximate graph edit distance by several local searches in parallel
Solving or approximating the linear sum assignment problem (LSAP) is an important step of
several constructive and local search strategies developed to approximate the graph edit …
several constructive and local search strategies developed to approximate the graph edit …
A parallel algorithm for subgraph isomorphism
In different application fields, such as biology, databases, social networks and so on, graphs
are a widely adopted structure to represent the data. In these fields, a relevant problem is the …
are a widely adopted structure to represent the data. In these fields, a relevant problem is the …
Fast linear sum assignment with error-correction and no cost constraints
We propose an algorithm that efficiently solves the linear sum assignment problem with error-
correction and no cost constraints. This problem is encountered for instance in the …
correction and no cost constraints. This problem is encountered for instance in the …
Graph node matching for edit distance
Graphs are commonly used to model interactions between elements of a set, but computing
the Graph Edit Distance between two graphs is an NP-complete problem that is particularly …
the Graph Edit Distance between two graphs is an NP-complete problem that is particularly …