Skip to content

QSVM on Graph Data to Preserve Topological Structure for Classification

Notifications You must be signed in to change notification settings

OsamaMIT/qsvm-graph-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 

Repository files navigation

QSVM for Graph Learning that Preserves Topological Structure

About

Part of research on implementing quantum support vector machines on multi-dimensional graph based data to preserve its topogical strucutre for more meainingful classification. Mainly trained on TUDataset's PROTEINS and MUTAG datasets for the classification of biological molecules.

Accuracy

Scored by 10-Fold Cross-Validation

PROTEINS - 74.48% ± 3.75

MUTAG - 83.48% ± 6.61

Model Highlights

  1. Preserves topological structure of graph data
  2. Consistent sub 3:00 training time
  3. Relatively simple feature map
  4. Highly interpretable model

The included ipynb file only includes the code regarding the final model.

About

QSVM on Graph Data to Preserve Topological Structure for Classification

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published