提出新型多视图聚类方法，通过粒度球体建模局部结构并增强跨视图对比。
Multi-view Granular-ball Contrastive Clustering
- 用粒度球体连接样本，实现细粒度与粗粒度的多层次对比学习。
- 在多个数据集上优于现有方法，聚类准确率提升显著。
- 适合处理具有复杂局部结构的多视图数据，如图像和文本融合任务。
以往的多视图对比学习方法通常在实例级和聚类级两个尺度上操作。实例级方法基于样本对应关系构建正负对，目标是在潜在空间中拉近正样本对、推远负样本对；聚类级方法则关注各视图下样本的聚类分配，通过减小分布差异（如最小化KL散度或最大化互信息）来增强视图一致性。然而，这两类方法分别存在引入错误负样本导致模型判别力下降，或忽略局部结构且无法显式衡量跨视图聚类间关系的问题。为此，我们提出多视图粒度球对比聚类（MGBCC）。该方法将样本集划分为粗粒度的粒度球，并建立视图内与跨视图粒度球之间的关联，在共享潜在空间中强化这些关联，从而实现多粒度对比学习。粒度球介于实例与聚类之间，自然保留了样本集的局部拓扑结构。我们通过大量实验验证了所提方法的有效性。
原文摘要 · Abstract (English)
Previous multi-view contrastive learning methods typically operate at two scales: instance-level and cluster-level. Instance-level approaches construct positive and negative pairs based on sample correspondences, aiming to bring positive pairs closer and push negative pairs further apart in the latent space. Cluster-level methods focus on calculating cluster assignments for samples under each view and maximize view consensus by reducing distribution discrepancies, e.g., minimizing KL divergence or maximizing mutual information. However, these two types of methods either introduce false negatives, leading to reduced model discriminability, or overlook local structures and cannot measure relationships between clusters across views explicitly. To this end, we propose a method named Multi-view Granular-ball Contrastive Clustering (MGBCC). MGBCC segments the sample set into coarse-grained granular balls, and establishes associations between intra-view and cross-view granular balls. These associations are reinforced in a shared latent space, thereby achieving multi-granularity contrastive learning. Granular balls lie between instances and clusters, naturally preserving the local topological structure of the sample set. We conduct extensive experiments to validate the effectiveness of the proposed method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。