I. Introduction
Internet of Everything (IoE) expands on the concept of the Internet of Things (IoT) by not only connecting devices and objects but also integrating people, processes, and data, etc., this integration creates a more intelligent and connected environment for graph computing-guided data analysis. Among the different graph mining algorithms, graph neural network is widely used in various fields due to its powerful learning ability, especially for real-world application scenarios like IoE, including node classification [1], link prediction [2], and node clustering [3]. Unsupervised graph clustering, a task that endeavors to aggregate nodes into distinct groups, faces numerous challenges. Recently, contrastive learning [4], as a robust learning paradigm, has ushered in new breakthroughs for graph clustering, it intends to enhance the proximity between semantically similar positive pairs while simultaneously pushing apart negative sample pairs, thereby constructing effective graph node representations.