The prevalence of graph-based data has spurred the rapid development of graph neural networks (GNNs) and related machine learning algorithms. Yet, despite the many datasets …
Abstract Graph Contrastive Learning (GCL) has emerged to learn generalizable representations from contrastive views. However, it is still in its infancy with two concerns: 1) …
Abstract Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data. However, while many real-world graphs are directed, the majority …
Y He, Q Gan, D Wipf, GD Reinert… - international …, 2022 - proceedings.mlr.press
Recovering global rankings from pairwise comparisons has wide applications from time synchronization to sports team ranking. Pairwise comparisons corresponding to matches in …
Signed and directed networks are ubiquitous in real-world applications. However, there has been relatively little work proposing spectral graph neural networks (GNNs) for such …
Y He, X Zhang, J Huang… - Learning on Graphs …, 2024 - proceedings.mlr.press
Networks are ubiquitous in many real-world applications (eg, social networks encoding trust/distrust relationships, correlation networks arising from time series data). While many …
H Yoo, YC Lee, K Shin, SW Kim - … of the ACM Web Conference 2023, 2023 - dl.acm.org
The goal of directed network embedding is to represent the nodes in a given directed network as embeddings that preserve the asymmetric relationships between nodes. While a …
This paper introduces SigMaNet, a generalized Graph Convolutional Network (GCN) capable of handling both undirected and directed graphs with weights not restricted in sign …
Y Zhao, J Qi, Q Liu, R Zhang - Proceedings of the 44th International ACM …, 2021 - dl.acm.org
Graph structural information such as topologies or connectivities provides valuable guidance for graph convolutional networks (GCNs) to learn nodes' representations. Existing …