Graph-based semi-supervised learning (GSSL) has attracted great attention over the past decade. However, there are still several open problems: (1) how to construct a graph that effectively represents ...

Graph Neural Networks (GNNs) are a class of neural networks designed to operate directly on graph-structured data. They enable the modeling of complex relationships and structures present in graphs, ...

This repo is the implementation of "Data augmentation techniques on graph structures for table type classification" paper, submitted to S+SSPR 2022 workshop. Once our work will be accepted, we will ...

Few-shot graph classification, as one application of meta-learning in supervised graph learning, aims to classify unseen graph types by only using a small amount of labeled data. However, the current ...

To classify multiple seizure types from EEG data, this model introduces IDGL to optimize the input graph structure, addressing the limitations of predefined prior graphs in traditional methods. By ...