Tensor Representation-Based Multiview Graph Contrastive Learning for IoE Intelligence

As a prevalent computing paradigm, graph computing provides an effective service strategy for the analysis of big data within the Internet of Everything (IoE), particularly for clustering graph-structured data in the IoE. Among various methods, graph contrastive clustering, which is devoted to revealing the intrinsic structure of graphs and efficiently grouping nodes into distinct clusters by contrasting positive-negative counterparts, has attracted widely attention in recent years. However, the existing methods seriously ignore the graph topology and node attributes when setting positive and negative sample pairs, which further leads to node semantic inconsistency. To this end, we design a novel tensor representation-based multiview contrastive graph representation learning framework, including adaptive data augmentation, high-confidence sample pairs construction, and a simple yet effective self-optimizing module guided by clustering objective function, to address issues of graph contrastive learning in ignoring complementary information among the topology and attributes. Specifically, by jointly modeling the graph structure and multiview node attributes, the new proposed clustering model can concurrently mine both hard positive and negative samples, and dynamically enhance the weight allocation of the hard samples during the learning process. Then leveraging the characteristics of graph-structured data, we incorporate a small subset of nodes with the highest similarity as additional positive samples to improve the discriminative power of the proposed model. Furthermore, a self-optimizing clustering module is introduced to enhance the algorithm’s performance. Experimental results on four commonly used IoE-related data sets validate that our proposed approach can achieve state-of-the-art clustering performance.

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.