Federated learning (FL), which provides a collaborative training scheme for distributed data
sources with privacy concerns, has become a burgeoning and attractive research area. Most …

Federated learning shows a bright promise as a privacy-preserving collaborative learning
technique. However, prevalent solutions mainly focus on all private data sampled from the …

Graph neural networks (GNNs) have shown their superiority in modeling graph data. Owing
to the advantages of federated learning, federated graph learning (FGL) enables clients to …

Graph contrastive learning (GCL) alleviates the heavy reliance on label information for
graph representation learning (GRL) via self-supervised learning schemes. The core idea is …

Federated learning is a new learning paradigm that decouples data collection and model
training via multi-party computation and model aggregation. As a flexible learning setting …

While" instruction-tuned" generative large language models (LLMs) have demonstrated an
impressive ability to generalize to new tasks, the training phases heavily rely on large …

Graph-level anomaly detection (GLAD) aims to identify graphs that exhibit notable
dissimilarity compared to the majority in a collection. However, current works primarily focus …

The intersection of the Foundation Model (FM) and Federated Learning (FL) provides mutual
benefits, presents a unique opportunity to unlock new possibilities in AI research, and …

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

Pre-training is prevalent in nowadays deep learning to improve the learned model's
performance. However, in the literature on federated learning (FL), neural networks are …