Abstract Knowledge graph (KG) embeddings have shown great power in learning
representations of entities and relations for link prediction tasks. Previous work usually …

Recommender systems are essential to various fields, eg, e-commerce, e-learning, and
streaming media. At present, graph neural networks (GNNs) for session-based …

Abstract Graph Neural Networks are effective in learning representations of graph-structured
data. Some recent works are devoted to addressing heterophily, which exists ubiquitously in …

Abstract Graph Neural Networks (GNNs) have been a prevailing technique for tackling
various analysis tasks on graph data. A key premise for the remarkable performance of …

Graph neural networks are essential in mining complex relationships in graphs. However,
most methods ignore the global location information of nodes and the discrepancy between …

Traffic prediction is an important component of the intelligent transportation system. Existing
deep learning methods encode temporal information and spatial information separately or …

Text classification is a quintessential and practical problem in natural language processing
with applications in diverse domains such as sentiment analysis, fake news detection …

Graph-Convolution-based methods have been successfully applied to representation
learning on homophily graphs where nodes with the same label or similar attributes tend to …

Abstract Graph Contrastive Learning (GCL) has recently enjoyed great success as an
efficient self-supervised representation learning approach. However, the existing methods …

Multilayer graphs have received significant research attention in numerous areas beacause
of their high utility in modeling interdependent systems. However, clustering of the multilayer …