Abstract Heterogeneous Graph Contrastive Learning (HGCL) has attracted lots of attentions
because of eliminating the requirement of node labels. The encoders used in HGCL mainly …

Graph pooling has been increasingly recognized as crucial for Graph Neural Networks
(GNNs) to facilitate hierarchical graph representation learning. Existing graph pooling …

In recent years, graph neural networks have achieved remarkable performance in various
downstream tasks by aggregating node neighborhoods hierarchically. However, prior …

Social media has transformed the landscape of news dissemination, characterized by its
rapid, extensive, and diverse content, coupled with the challenge of verifying authenticity …

With the significant reduction in the cost of image manipulation due to advancements in
image editing tools, it is crucial to investigate methods for detecting image manipulation …

Cross-modal recipe retrieval is vital for transforming visual food cues into actionable cooking
guidance, making culinary creativity more accessible. Existing methods separately encode …

The recently released ChatGPT, an artificial intelligence conversational agent, has garnered
significant attention in academia and real life. A multitude of early ChatGPT users have …

This paper investigates self-supervised graph representation learning, addressing the
challenges posed by noise and ambiguity inherent in graph data, which often result in low …