Simple Network Graph Comparative Learning
Qiang Yu, Xinran Cheng, Shiqiang Xu, Chuanyi Liu
TL;DR
This work tackles the efficiency and effectiveness challenges of graph contrastive learning for node classification by introducing SNGCL, which generates robust views through a superimposed multilayer Laplace smoothing filter to produce global and local feature matrices. A momentum-guided siamese network processes these views, while a triple recombination loss coupled with an upper-bound term enforces stronger inter-class separation and tighter intra-class consistency without heavy reliance on negatives. Extensive experiments across five real-world datasets show SNGCL achieving competitive or superior accuracy compared to a wide range of baselines, with notable gains on the Amazon-Photo dataset and clear ablation support for the global/local smoothing and loss design. The approach offers a scalable, high-quality representation learning paradigm for unsupervised graph learning with practical implications for node classification tasks in large graphs.
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.