Research map / Graph learning / Graph self-supervised learning
iGraphMix: Input Graph Mixup Method for Node Classification
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 iGraphMix, an input mixup method adapted to graph node classification that interpolates node features, labels and graph structure to reduce over-fitting.
Problem
Input Mixup is effective in images and NLP but hard to design for node classification on graphs, where nodes are non-independent and connected by edges; the paper targets over-fitting in GNN node classification.
Approach
Extends input mixup to graph-structured data by generating virtual samples through interpolation of node input features and labels while accounting for graph connectivity, rather than treating nodes as independent samples.
Experimental setup
Builds on: Input Mixup
Closest papers by meaning
- IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors (NeurIPS 2024 · similarity 0.93)
- AGMixup: Adaptive Graph Mixup for Semi-supervised Node Classification (AAAI 2025 · similarity 0.91)
- NodeMixup: Tackling Under-Reaching for Graph Neural Networks (AAAI 2024 · similarity 0.89)
- Graph Mixup on Approximate Gromov–Wasserstein Geodesics (ICML 2024 · similarity 0.86)
- Graph Invariant Learning with Subgraph Co-mixup for Out-of-Distribution Generalization (AAAI 2024 · similarity 0.85)
- NLGT: Neighborhood-based and Label-enhanced Graph Transformer Framework for Node Classification (AAAI 2025 · similarity 0.85)
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.