Research map / Graph learning / Knowledge and temporal graphs
UniHG: A Large-scale Universal Heterogeneous Graph Dataset and Benchmark for Representation Learning and Cross-Domain Transferring
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Constructs UniHG, a large-scale universal multi-domain heterogeneous graph dataset and benchmark for representation learning and cross-domain transfer.
Problem
Heterogeneous graph research faces benchmark deficiency, semantic disalignment across node/edge types, and propagation degradation.
Approach
A large-scale joint multi-domain heterogeneous graph dataset intended to address benchmark scarcity and enable cross-domain transfer learning on heterogeneous graphs.
Closest papers by meaning
- HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily (NeurIPS 2026 · similarity 0.90)
- Harnessing Language Model for Cross-Heterogeneity Graph Knowledge Transfer (AAAI 2025 · similarity 0.89)
- Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach (AAAI 2025 · similarity 0.89)
- TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs (NeurIPS 2024 · similarity 0.88)
- An Efficient Subgraph-Inferring Framework for Large-Scale Heterogeneous Graphs (AAAI 2024 · similarity 0.88)
- Heterogeneous Graph Neural Network on Semantic Tree (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.