Solving inexact graph isomorphism problems using neural networks
2005
We present a neural network approach to solve exact and inexact graph isomorphism problems for weighted graphs. In contrast to other neural heuristics or related methods this approach is based on a neural refinement procedure to reduce the search space followed by an energy-minimizing matching process. Experiments on random weighted graphs in the range of 100-5000 vertices and on chemical molecular structures are presented and discussed.
Keywords:
- Graph canonization
- Graph isomorphism
- Subgraph isomorphism problem
- Graph homomorphism
- Mathematical optimization
- Graph power
- Coxeter graph
- Discrete mathematics
- Voltage graph
- Factor-critical graph
- Mathematics
- Line graph
- Pattern recognition
- Block graph
- Theoretical computer science
- Graph property
- Artificial intelligence
- Split graph
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
45
References
13
Citations
NaN
KQI