Ling Tian

Federal Graph Contrastive Learning With Secure Cross-Device Validation

2024 · IEEE Transactions on Mobile Computing

Distributed mobile devices collect unlabeled graph data from environment. Introducing popular graph contrastive learning (GCL) methods can learn node representations better. However, training high-performance GCL requires large-scale data and graph data collected by the single …

Hybrid knowledge reasoning over knowledge hypergraph: Inductive, deductive, and abductive

2026 · Journal of Electronic Science and Technology

Traditional knowledge reasoning methods, which are predominantly reliant on static rules and structured data, often struggle to adapt to the ambiguity and dynamic evolution of real-world scenarios. To overcome these limitations, this study proposes a …