MDL-GBC constructs class-conditional granular balls by comparing single-ball, two-ball, and core-boundary models under a unified MDL criterion and aggregates them for prediction, achieving the best average accuracy and Macro-F1 on 18 benchmarks.
Granular ball computing: an efficient, robust, and interpretable adaptive multi-granularity representation and computation method
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
MDL-GBG selects the shortest-description-length model among single-ball, two-ball, and core-ball-plus-residual options to generate stable granular balls that improve downstream clustering on UCI datasets.
MDL-GBTRSC constructs a granular-ball tree with local MDL selection and reciprocal neighborhood continuity to regularize the affinity graph in spectral clustering.
A multi-granularity granular-ball coarsening algorithm reduces large graphs in linear time for faster GCN training on node classification, with experiments claiming superior performance over prior methods.
citing papers explorer
-
A Boundary-Aware Non-parametric Granular-Ball Classifier Based on Minimum Description Length
MDL-GBC constructs class-conditional granular balls by comparing single-ball, two-ball, and core-boundary models under a unified MDL criterion and aggregates them for prediction, achieving the best average accuracy and Macro-F1 on 18 benchmarks.
-
MDL-GBG: A Non-parametric and Interpretable Granular-Ball Generation Method for Clustering
MDL-GBG selects the shortest-description-length model among single-ball, two-ball, and core-ball-plus-residual options to generate stable granular balls that improve downstream clustering on UCI datasets.
-
Minimum Description Length based Granular-Ball Tree Regularization for Spectral Clustering
MDL-GBTRSC constructs a granular-ball tree with local MDL selection and reciprocal neighborhood continuity to regularize the affinity graph in spectral clustering.
-
Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification
A multi-granularity granular-ball coarsening algorithm reduces large graphs in linear time for faster GCN training on node classification, with experiments claiming superior performance over prior methods.