Graph neural networks (GNNs) apply deep learning techniques to graph-structured data and have achieved promising performance in graph representation learning. However, existing GNNs rely heavily on labeled or well-designed negative samples. To address these issues, we propose a new self-supervised method: bootstrapping (DGB). DGB consists of two networks: online target networks, the input them ...

Deep learning methods have demonstrated promising performance on the NP-hard Graph Matching (GM) problems. However, state-of-the-art usually require ground-truth labels, which may take extensive human efforts or be impractical to collect. In this paper, we present a robust self-supervised bidirectional method (IA-SSGM) tackle GM in an unsupervised manner. It involves affinity component and clas...

Graph classification is a widely studied problem and has broad applications. In many real-world problems, the number of labeled graphs available for training models limited, which renders these prone to overfitting. To address this problem, we propose two approaches based on contrastive self-supervised learning (CSSL) alleviate first approach, use CSSL pretrain graph encoders widely-available u...

Introduction: Working in the complex and ever changinghealthcare settings forces the nurses and nursing students to beequipped with lifelong learning skills. One of the lifelong learningskills is self-directed learning. This study aimed to explore theM.Sc. nursing students’ self-directed learning activities.Methods: A qualitative design using conventional content analysisapproach was used in th...

The language Grace is being proposed for specifying and programming in a graph-centered environment based on graph transformation. Emphasis in the design of Grace is laid on modular structur-ing of programs. In this paper we present a simple kind of modules for the language which encapsulate rules and graph transformation units, and export some of them. The local transformation units deene comp...