Open Access

ARTICLE

Graph Similarity Learning Based on Learnable Augmentation and Multi-Level Contrastive Learning

Jian Feng^*, Yifan Guo, Cailing Du

College of Computer Science & Technology, Xi’an University of Science and Technology, Xi’an, 710054, China

* Corresponding Author: Jian Feng. Email:

(This article belongs to the Special Issue: Graph Neural Networks: Methods and Applications in Graph-related Problems)

Computers, Materials & Continua 2025, 82(3), 5135-5151. https://doi.org/10.32604/cmc.2025.059610

Received 12 October 2024; Accepted 19 December 2024; Issue published 06 March 2025

Abstract

Graph similarity learning aims to calculate the similarity between pairs of graphs. Existing unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph augmentation strategies, which can harm the semantic and structural information of graphs and overlook the rich structural information present in subgraphs. To address these issues, we propose a graph similarity learning model based on learnable augmentation and multi-level contrastive learning. First, to tackle the problem of random augmentation disrupting the semantics and structure of the graph, we design a learnable augmentation method to selectively choose nodes and edges within the graph. To enhance contrastive levels, we employ a biased random walk method to generate corresponding subgraphs, enriching the contrastive hierarchy. Second, to solve the issue of previous work not considering multi-level contrastive learning, we utilize graph convolutional networks to learn node representations of augmented views and the original graph and calculate the interaction information between the attribute-augmented and structure-augmented views and the original graph. The goal is to maximize node consistency between different views and learn node matching between different graphs, resulting in node-level representations for each graph. Subgraph representations are then obtained through pooling operations, and we conduct contrastive learning utilizing both node and subgraph representations. Finally, the graph similarity score is computed according to different downstream tasks. We conducted three sets of experiments across eight datasets, and the results demonstrate that the proposed model effectively mitigates the issues of random augmentation damaging the original graph’s semantics and structure, as well as the insufficiency of contrastive levels. Additionally, the model achieves the best overall performance.

---

Keywords

---