提升图聚类的特征多样性，让聚类结果更清晰可解释
Deep Modularity Networks with Diversity-Preserving Regularization
- 引入三种正则化：距离、方差和熵，增强聚类分离与分布均匀性
- 在多个基准数据集上显著提升聚类指标（p≤0.05）
- 适合需要可解释聚类结果的研究者，如社交网络分析
图聚类在图表示学习中至关重要，但常面临特征空间多样性不足的问题。尽管深度模块网络（DMoN）通过最大化模块度和坍缩正则化实现结构分离，却缺乏对特征空间分离、分配分散性和置信度控制的显式机制。本文提出带多样性保持正则化的深度模块网络（DMoN-DPR），引入三种新正则项：基于距离的簇间分离、基于方差的簇内分配分散性，以及带小权重的分配熵惩罚，逐步促进更自信的聚类分配。实验表明，该方法在特征丰富的基准数据集上显著提升基于标签的聚类指标（配对双尾t检验，p≤0.05），证明了多样性保持正则化在生成有意义且可解释聚类中的有效性。
原文摘要 · Abstract (English)
Graph clustering plays a crucial role in graph representation learning but often faces challenges in achieving feature-space diversity. While Deep Modularity Networks (DMoN) leverage modularity maximization and collapse regularization to ensure structural separation, they lack explicit mechanisms for feature-space separation, assignment dispersion, and assignment-confidence control. We address this limitation by proposing Deep Modularity Networks with Diversity-Preserving Regularization (DMoN-DPR), which introduces three novel regularization terms: distance-based for inter-cluster separation, variance-based for per-cluster assignment dispersion, and an assignment-entropy penalty with a small positive weight, encouraging more confident assignments gradually. Our method significantly enhances label-based clustering metrics on feature-rich benchmark datasets (paired two-tailed t-test, $p\leq0.05$), demonstrating the effectiveness of incorporating diversity-preserving regularizations in creating meaningful and interpretable clusters.
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。