Simple Network Graph Comparative Learning

TL;DR

This paper introduces SNGCL, a contrastive learning method for node classification on graphs that uses Laplace smoothing and an improved loss function to enhance feature relevance and reduce reliance on negative samples.

Contribution

SNGCL is a novel contrastive learning approach that employs Laplace smoothing and a new loss function to improve node classification without extensive negative sampling.

Findings

SNGCL outperforms several state-of-the-art models in node classification tasks.

The method effectively enhances feature relevance through Laplace smoothing.

Experimental results demonstrate strong competitiveness of SNGCL.

Abstract

The effectiveness of contrastive learning methods has been widely recognized in the field of graph learning, especially in contexts where graph data often lack labels or are difficult to label. However, the application of these methods to node classification tasks still faces a number of challenges. First, existing data enhancement techniques may lead to significant differences from the original view when generating new views, which may weaken the relevance of the view and affect the efficiency of model training. Second, the vast majority of existing graph comparison learning algorithms rely on the use of a large number of negative samples. To address the above challenges, this study proposes a novel node classification contrast learning method called Simple Network Graph Comparative Learning (SNGCL). Specifically, SNGCL employs a superimposed multilayer Laplace smoothing filter as a step in processing the data to obtain global and local feature smoothing matrices, respectively, which are thus passed into the target and online networks of the siamese network, and finally employs an improved triple recombination loss function to bring the intra-class distance closer and the inter-class distance farther. We have compared SNGCL with state-of-the-art models in node classification tasks, and the experimental results show that SNGCL is strongly competitive in most tasks.