Bachelor Thesis Open Access

One-Shot Neural Inference for Latent Space Clustering in GNN-Based Track Finding at Belle II

Großmann, Daniel Micha

JSON-LD (schema.org) Export

{
  "@context": "https://schema.org/", 
  "@type": "ScholarlyArticle", 
  "contributor": [], 
  "creator": [
    {
      "@type": "Person", 
      "affiliation": "KIT/ETP", 
      "name": "Gro\u00dfmann, Daniel Micha"
    }
  ], 
  "datePublished": "2026-04-01", 
  "description": "<p>This thesis proposes a one-shot neural clustering algorithm for object condensation pipelines. The algorithm groups an unordered input point cloud of variable count with latent space representations of the input hits into a variable number of clusters and differentiates between signal and noise. Implementation and evaluation is done in the graph neural network based track-finding pipeline for the Belle II central drift chamber. In a first<br>\nstep, the clustering pipeline and machine learning architecture are presented, combining key solutions from different computer vision pipelines. Next, the required hyperparameters are fitted using simulated detector samples, showing a good generalization across vastly differing event topologies. Then, the clustering is evaluated on a diverse set of<br>\nchallenging events, leveraging a realistic detector simulation combined with high levels of detector noise measured in actual collisions. Additional validation is performed directly on measured collision data with high levels of detector noise, showing real-world applicability and robustness. The evaluation shows a significant improvement in track charge efficiency<br>\nand clone rate, while retaining a similar fake rate. When benchmarked against state of the art classical clustering algorithms, the one-shot neural inference provides a significant speedup without sacrificing clustering quality.</p>", 
  "headline": "One-Shot Neural Inference for Latent Space Clustering in GNN-Based Track Finding at Belle II", 
  "image": "https://publish.etp.kit.edu/static/img/logos/zenodo-gradient-round.svg", 
  "inLanguage": {
    "@type": "Language", 
    "alternateName": "eng", 
    "name": "English"
  }, 
  "keywords": [
    "machine learning", 
    "tracking", 
    "pointcloud", 
    "clustering"
  ], 
  "name": "One-Shot Neural Inference for Latent Space Clustering in GNN-Based Track Finding at Belle II", 
  "url": "https://publish.etp.kit.edu/record/22427"
}
Publication date:
April 1, 2026
Keyword(s):
machine learning tracking pointcloud clustering
Awarding University:
Karlsruhe Institute of Technology (KIT)
Report Number:
ETP-BACHELOR-KA/2026-03
Communities:

Cite as

Export