Research map / Graph learning / Knowledge and temporal graphs
Defining and Discovering Hyper-meta-paths for Heterogeneous Hypergraphs
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.
Defines hyper-meta-paths for heterogeneous hypergraphs and proposes a method to discover them for representation learning.
Problem
Representation learning for heterogeneous hypergraphs, which have multiple node types and multiple hyperedge types encoding multi-ary hyper-relations, is underexplored; existing methods learn node and hyperedge embeddings without capturing higher-order composite relations.
Approach
Extends meta-paths to hypergraphs by defining hyper-meta-paths that compose hyper-relations, and discovers useful ones automatically rather than relying on hand-designed paths.
Experimental setup
Builds on: meta-path
Closest papers by meaning
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.91)
- Hypergraph Representation Learning with Hyperlink Random Effects (NeurIPS 2026 · similarity 0.90)
- Heterogeneous Graph Neural Network on Semantic Tree (AAAI 2025 · similarity 0.90)
- SPHINX: Structural Prediction using Hypergraph Inference Network (ICML 2025 · similarity 0.90)
- K-hop Hypergraph Neural Network: A Comprehensive Aggregation Approach (AAAI 2025 · similarity 0.90)
- Hypergraph-enhanced Dual Semi-supervised Graph Classification (ICML 2024 · similarity 0.89)
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.