基于度量嵌入初始化的私密可解释图聚类方法
Metric Embedding Initialization-Based Differentially Private and Explainable Graph Clustering
- 用度量嵌入初始化提升聚类起始点质量
- 在多个数据集上优于现有方法且严格保隐私
- 适合需要隐私保护与结果解释的图分析场景
在差分隐私框架下的图聚类，旨在处理图结构数据的同时保护个体隐私，受到越来越多关注。尽管已有研究取得显著进展，但高噪声、低效率和可解释性差等问题仍严重制约该领域发展。本文提出一种基于度量嵌入初始化的差分隐私可解释图聚类方法。具体地，构建了一个SDP优化问题，提取关键节点集，并采用基于HST的初始化方法提供良好的聚类初始配置。随后，应用成熟的k-median聚类策略得到聚类结果，并通过查询集与聚类中心的差异提供对比解释。在多个公开数据集上的大量实验表明，所提框架在各类聚类指标上均优于现有方法，同时严格保证隐私。
原文摘要 · Abstract (English)
Graph clustering under the framework of differential privacy, which aims to process graph-structured data while protecting individual privacy, has been receiving increasing attention. Despite significant achievements in current research, challenges such as high noise, low efficiency and poor interpretability continue to severely constrain the development of this field. In this paper, we construct a differentially private and interpretable graph clustering approach based on metric embedding initialization. Specifically, we construct an SDP optimization, extract the key set and provide a well-initialized clustering configuration using an HST-based initialization method. Subsequently, we apply an established k-median clustering strategy to derive the cluster results and offer comparative explanations for the query set through differences from the cluster centers. Extensive experiments on public datasets demonstrate that our proposed framework outperforms existing methods in various clustering metrics while strictly ensuring privacy.
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。