# Granular-ball computing: an efficient, robust, and interpretable adaptive multi-granularity representation and computation method

arXiv: https://arxiv.org/abs/2304.11171 · HTML: https://mlsanity.com/paper/2304.11171/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 61 references that are in the map.
- First posted on arXiv 21 Apr 2023.

## Builds on (most cited first, 15 of 15)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [An Efficient and Adaptive Granular-ball Generation Method in Classification Problem](https://mlsanity.com/paper/2201.04343/) (2022)
- [Textual Manifold-based Defense Against Natural Language Adversarial Examples](https://mlsanity.com/paper/2211.02878/) (2022)
- [Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization](https://mlsanity.com/paper/1805.12302/) (2018)
- [SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher](https://mlsanity.com/paper/2011.08908/) (2020)
- [A Unified Granular-ball Learning Model of Pawlak Rough Set and Neighborhood Rough Set](https://mlsanity.com/paper/2201.03349/) (2022)
- [GBSVM: Granular-ball Support Vector Machine](https://mlsanity.com/paper/2210.03120/) (2022)
- [An Efficient and Accurate Rough Set for Feature Selection, Classification and Knowledge Representation](https://mlsanity.com/paper/2201.00436/) (2021)
- [GBC: An Efficient and Adaptive Clustering Algorithm Based on Granular-Ball](https://mlsanity.com/paper/2205.14592/) (2022)
- [Graph-based Representation for Image based on Granular-ball](https://mlsanity.com/paper/2303.02388/) (2023)
- [GBO:AMulti-Granularity Optimization Algorithm via Granular-ball for Continuous Problems](https://mlsanity.com/paper/2303.12807/) (2023)
- [GBMST: An Efficient Minimum Spanning Tree Clustering Based on Granular-Ball Computing](https://mlsanity.com/paper/2303.01082/) (2023)

## Built on by (most cited first, 16 of 16)

- [Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training](https://mlsanity.com/paper/2412.13842/) (2024)
- [Open Continual Feature Selection via Granular-Ball Knowledge Transfer](https://mlsanity.com/paper/2403.10253/) (2024)
- [Generation of Granular-Balls for Clustering Based on the Principle of Justifiable Granularity](https://mlsanity.com/paper/2405.06904/) (2024)
- [Granular Ball Twin Support Vector Machine with Universum Data](https://mlsanity.com/paper/2412.03375/) (2024)
- [GBGC: Efficient and Adaptive Graph Coarsening via Granular-ball Computing](https://mlsanity.com/paper/2506.19224/) (2025)
- [MDL-GBG: A Non-parametric and Interpretable Granular-Ball Generation Method for Clustering](https://mlsanity.com/paper/2605.08759/) (2026)
- [Granular Ball K-Class Twin Support Vector Classifier](https://mlsanity.com/paper/2412.05438/) (2024)
- [Granular Ball Guided Masking: Structure-aware Data Augmentation](https://mlsanity.com/paper/2512.21011/) (2025)
- [A Boundary-Aware Non-parametric Granular-Ball Classifier Based on Minimum Description Length](https://mlsanity.com/paper/2605.11406/) (2026)
- [GBSVR: Granular Ball Support Vector Regression](https://mlsanity.com/paper/2503.10539/) (2025)
- [Implicit Non-Causal Factors are Out via Dataset Splitting for Domain Generalization Object Detection](https://mlsanity.com/paper/2601.19127/) (2026)
- [Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting](https://mlsanity.com/paper/2603.24106/) (2026)
- [Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification](https://mlsanity.com/paper/2603.29148/) (2026)
- [Minimum Description Length based Granular-Ball Tree Regularization for Spectral Clustering](https://mlsanity.com/paper/2605.22410/) (2026)
- [3DGBGS: 3D Granular Ball Gaussian Splatting for Compact Novel View Synthesis](https://mlsanity.com/paper/2607.26578/) (2026)
- [Robust and Efficient Noisy-Label Time-Series Classification via Dynamic Time Warping Based Granular Ball Computing](https://mlsanity.com/paper/2608.11704/) (2026)

## Abstract (arXiv)

To overcome the limitations of point-based inputs, overly fine computation and limited adaptability in existing artificial intelligence methods, Guoyin Wang and Shuyin Xia proposed granular-ball computing as a new artificial intelligence learning paradigm. Unlike traditional clustering, which mainly performs macro-level grouping, granular-ball computing uses differently sized hyperspheres, termed granular balls, as mesoscopic representation units; rectangles and ellipsoids can serve as approximate balls in low-dimensional spaces. It adaptively fits arbitrary data distributions, replacing traditional artificial intelligence computation based on fine-grained point inputs or single-granularity modeling and establishing a new theoretical paradigm for artificial intelligence based on granular balls. It aims to build an end-to-end multigranular artificial intelligence framework that improves the efficiency, robustness, and interpretability of existing methods. Recently, this theory has advanced rapidly and yielded representative results, yet it still lacks a unified model for systematic summarization. Accordingly, this article first proposes a general representation model of granular-ball computing within a unified descriptive framework and systematically reviews its fundamental ideas and advances in granular-ball computing across granular-ball supervised learning, granular-ball unsupervised learning, approximate granular-ball representation and computation, granular-ball deep learning based on latent-space granulation, granular-ball graph learning, and granular-ballinterdisciplinary research. Further, it identifies open challenges and outlines future research directions.