LoGCC: Local-to-Global Correlation Clustering for Scalar Field Ensembles

Information

• Publication Type: Journal Paper (without talk)
• Workgroup(s)/Project(s): not specified
• Date: February 2026
• DOI: 10.1109/TVCG.2025.3630550
• ISSN: 1941-0506
• Journal: IEEE Transactions on Visualization and Computer Graphics
• Number: 2
• Pages: 12
• Volume: 32
• Publisher: IEEE COMPUTER SOC
• Pages: 2260 – 2271
• Keywords: Correlation Clustering, Clustering Algorithms, Uncertainty Visualization, Ensemble Visualization, Scalar Field Ensemble Analysis

Abstract

Correlation clustering (CC) offers an effective approach to analyze scalar field ensembles by detecting correlated regions and consistent structures, enabling the extraction of meaningful patterns. However, existing CC methods are computationally expensive, making them impractical for both interactive analysis and large-scale scalar fields. We introduce the Local-to-Global Correlation Clustering (LoGCC) framework, which accelerates pivot-based CC by leveraging the spatial structure of scalar fields and the weak transitivity of correlation. LoGCC operates in two stages: a local step that uses the neighborhood graph of the scalar field's spatial domain to build highly correlated local clusters, and a global step that merges them into global clusters. We implement the LoGCC framework for two well-known pivot-based CC methods, Pivot and CN-Pivot, demonstrating its generality. Our evaluation using synthetic and real-world meteorological and medical image segmentation datasets shows that LoGCC achieves speedups—up to 15 × for Pivot and 200 × for CN-Pivot—and improved scalability to larger scalar fields, while maintaining cluster quality. These contributions broaden the applicability of correlation clustering in large-scale and interactive analysis settings.

Additional Files and Images

Weblinks

• Entry in reposiTUm (TU Wien Publication Database)
• DOI: 10.1109/TVCG.2025.3630550

BibTeX

@article{chaves-de-plaza-2026-logcc,
  title =      "LoGCC: Local-to-Global Correlation Clustering for Scalar
               Field Ensembles",
  author =     "Nicolas F. Chaves-de-Plaza and Renata Raidou and Prerak Mody
               and Marius Staring and Ren\'{e} Van Egmond and Anna Vilanova
               and Klaus Hildebrandt",
  year =       "2026",
  abstract =   "Correlation clustering (CC) offers an effective approach to
               analyze scalar field ensembles by detecting correlated
               regions and consistent structures, enabling the extraction
               of meaningful patterns. However, existing CC methods are
               computationally expensive, making them impractical for both
               interactive analysis and large-scale scalar fields. We
               introduce the Local-to-Global Correlation Clustering (LoGCC)
               framework, which accelerates pivot-based CC by leveraging
               the spatial structure of scalar fields and the weak
               transitivity of correlation. LoGCC operates in two stages: a
               local step that uses the neighborhood graph of the scalar
               field's spatial domain to build highly correlated local
               clusters, and a global step that merges them into global
               clusters. We implement the LoGCC framework for two
               well-known pivot-based CC methods, Pivot and CN-Pivot,
               demonstrating its generality. Our evaluation using synthetic
               and real-world meteorological and medical image segmentation
               datasets shows that LoGCC achieves speedups—up to 15 ×
               for Pivot and 200 × for CN-Pivot—and improved scalability
               to larger scalar fields, while maintaining cluster quality.
               These contributions broaden the applicability of correlation
               clustering in large-scale and interactive analysis settings.",
  month =      feb,
  doi =        "10.1109/TVCG.2025.3630550",
  issn =       "1941-0506",
  journal =    "IEEE Transactions on Visualization and Computer Graphics",
  number =     "2",
  pages =      "12",
  volume =     "32",
  publisher =  "IEEE COMPUTER SOC",
  pages =      "2260--2271",
  keywords =   "Correlation Clustering, Clustering Algorithms, Uncertainty
               Visualization, Ensemble Visualization, Scalar Field Ensemble
               Analysis",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2026/chaves-de-plaza-2026-logcc/",
}