Shaoxiang Ling

UniHG: A Large-scale Universal Heterogeneous Graph Dataset and Benchmark for Representation Learning and Cross-Domain Transferring

Irregular data in the real world are usually organized as heterogeneous graphs consisting of multiple types of nodes and edges. However, current heterogeneous graph research confronts three fundamental challenges: i) Benchmark Deficiency, ii) Semantic Disalignment, and iii) Propagation Degradation.…