Automatic radiology reporting has great clinical potential to relieve radiologists from heavy
workloads and improve diagnosis interpretation. Recently, researchers have enhanced data …

Federated Learning (FL) is a machine learning paradigm that allows decentralized clients to
learn collaboratively without sharing their private data. However, excessive computation and …

Large language models (LLMs) have demonstrated impressive reasoning abilities in
complex tasks. However, they lack up-to-date knowledge and experience hallucinations …

Deep graph clustering, which aims to group the nodes of a graph into disjoint clusters with
deep neural networks, has achieved promising progress in recent years. However, the …

Graph self-supervised learning (SSL), including contrastive and generative approaches,
offers great potential to address the fundamental challenge of label scarcity in real-world …

Continuous-time dynamic graphs naturally abstract many real-world systems, such as social
and transactional networks. While the research on continuous-time dynamic graph …

Graph condensation, which reduces the size of a large-scale graph by synthesizing a small-
scale condensed graph as its substitution, has immediate benefits for various graph learning …

Unsupervised graph representation learning (UGRL) has drawn increasing research
attention and achieved promising results in several graph analytic tasks. Relying on the …

Real-world graphs generally have only one kind of tendency in their connections. These
connections are either homophilic-prone or heterophily-prone. While graphs with homophily …

Most existing deep learning models are trained based on the closed-world assumption,
where the test data is assumed to be drawn iid from the same distribution as the training …