🤖 AI Summary
Existing granular ball (GB) methods rely on k-means or k-division for ball generation, resulting in instability, low efficiency, and classifiers that exploit only geometric features while ignoring intra-ball sample quality.
Method: We propose GBG++, a data-driven, stable GB generation framework that eliminates k-means dependency via center-distance-adaptive computation, local outlier detection, and an attention-inspired distance-optimized splitting strategy—guaranteeing 100% generation stability. Further, we design GBkNN++, a granular-ball-quality-aware classifier that jointly models geometric structure and weighted intra-ball sample quality to enhance boundary discrimination.
Results: Evaluated on 24 benchmark datasets, GBG++/GBkNN++ consistently outperforms state-of-the-art granular ball classifiers and classical machine learning algorithms, achieving significantly faster runtime and substantially lower misclassification rates.
📝 Abstract
Granular ball computing (GBC), as an efficient, robust, and scalable learning method, has become a popular research topic of granular computing. GBC includes two stages: granular ball generation (GBG) and multi-granularity learning based on the granular ball (GB). However, the stability and efficiency of existing GBG methods need to be further improved due to their strong dependence on <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula>-means or <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula>-division. In addition, GB-based classifiers only unilaterally consider the GB's geometric characteristics to construct classification rules, but the GB's quality is ignored. Therefore, in this paper, based on the attention mechanism, a fast and stable GBG (GBG++) method is proposed first. Specifically, the proposed GBG++ method only needs to calculate the distances from the data-driven center to the undivided samples when splitting each GB instead of randomly selecting the center and calculating the distances between it and all samples. Moreover, an outlier detection method is introduced to identify local outliers. Consequently, the GBG++ method can significantly improve effectiveness, robustness, and efficiency while being absolutely stable. Second, considering the influence of the sample size within the GB on the GB's quality, based on the GBG++ method, an improved GB-based <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula>-nearest neighbors algorithm (GB<inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula>NN++) is presented, which can reduce misclassification at the class boundary. Finally, the experimental results indicate that the proposed method outperforms several existing GB-based classifiers and classical machine learning classifiers on 24 public benchmark datasets.
