arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.04741cs.LG
收藏

无需预定义簇数量k的图聚类掩码自编码器

Masked AutoEncoder for Graph Clustering without Pre-defined Cluster Number k

Yuanchi Ma, Hui He, Zhongxiang Lei, Zhendong Niu

AI总结:

针对图自编码器聚类泛化差且簇数难定的问题,提出GCMA框架,利用图掩码融合编码与改进密度聚类第二解码器端到端输出簇数并提升泛化。

摘要:

具有自编码器结构的图聚类算法因其高效性能和低训练成本而近期受到欢迎。然而,对于基于GCN或GAT的现有图自编码器聚类算法,不仅缺乏良好的泛化能力,而且此类自编码器模型聚类的簇数量也难以自动确定。为解决这一问题,我们提出了一种名为Graph Clustering with Masked Autoencoders(GCMA)的新框架。它采用我们设计的基于图掩码方法的融合自编码器对图进行融合编码。它引入我们改进的基于密度的聚类算法作为第二解码器,同时进行多目标重构解码。通过解码掩码嵌入,我们的模型能够捕获更泛化和全面的知识。在提升泛化能力的同时,能够端到端地输出簇数量和聚类结果。作为一种非参数方法,大量实验证明了GCMA优于最先进的基线方法。

英文摘要:

Graph clustering algorithms with autoencoder structures have recently gained popularity due to their efficient performance and low training cost. However, for existing graph autoencoder clustering algorithms based on GCN or GAT, not only do they lack good generalization ability, but also the number of clusters clustered by such autoencoder models is difficult to determine automatically. To solve this problem, we propose a new framework called Graph Clustering with Masked Autoencoders (GCMA). It employs our designed fusion autoencoder based on the graph masking method for the fusion coding of graph. It introduces our improved density-based clustering algorithm as a second decoder while decoding with multi-target reconstruction. By decoding the mask embedding, our model can capture more generalized and comprehensive knowledge. The number of clusters and clustering results can be output end-to-end while improving the generalization ability. As a nonparametric class method, extensive experiments demonstrate the superiority of \textit{GCMA} over state-of-the-art baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑