Research map / Graph learning / Graph self-supervised learning
HyperMixup: Hypergraph-Augmented with Higher-order Information Mixup
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.
Proposes HyperMixup, a hypergraph-augmented mixup method using higher-order information to address label scarcity and related challenges in hypergraph neural network learning.
Problem
Hypergraph neural networks suffer from scarce labeled data in complex higher-order relational systems, along with a second persistent bottleneck noted in the abstract (truncated).
Approach
Applies mixup-style data augmentation tailored to hypergraphs by incorporating higher-order (multi-way) structural information to generate augmented training samples.
Experimental setup
Builds on: mixup
Closest papers by meaning
- HyperNoRA: Hyperedge Prediction via Node-Level Relation-Aware Self-Supervised Hypergraph Learning (AAAI 2026 · similarity 0.91)
- SPHINX: Structural Prediction using Hypergraph Inference Network (ICML 2025 · similarity 0.90)
- Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport (AAAI 2025 · similarity 0.89)
- Beyond Graphs: Can Large Language Models Comprehend Hypergraphs? (ICLR 2025 · similarity 0.88)
- Hypergraph Joint Representation Learning for Hypervertices and Hyperedges via Cross Expansion (AAAI 2024 · similarity 0.88)
- Hypergraph-enhanced Dual Semi-supervised Graph Classification (ICML 2024 · similarity 0.87)
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.