# GraphMix: Improved Training of GNNs for Semi-Supervised Learning

arXiv: https://arxiv.org/abs/1909.11715 · HTML: https://mlsanity.com/paper/1909.11715/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2019.

## Built on by (most cited first, 23 of 23)

- [A Unified Lottery Ticket Hypothesis for Graph Neural Networks](https://mlsanity.com/paper/2102.06790/) (2021)
- [Graph Data Augmentation for Graph Machine Learning: A Survey](https://mlsanity.com/paper/2202.08871/) (2022)
- [Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks](https://mlsanity.com/paper/2104.07886/) (2021)
- [Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study](https://mlsanity.com/paper/2108.10521/) (2021)
- [On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers](https://mlsanity.com/paper/2102.07346/) (2021)
- [Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation](https://mlsanity.com/paper/2111.05639/) (2021)
- [Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations](https://mlsanity.com/paper/2201.01702/) (2022)
- [Model-Agnostic Augmentation for Accurate Graph Classification](https://mlsanity.com/paper/2202.10107/) (2022)
- [Informative Pseudo-Labeling for Graph Neural Networks with Few Labels](https://mlsanity.com/paper/2201.07951/) (2022)
- [Half-Hop: A graph upsampling approach for slowing down message passing](https://mlsanity.com/paper/2308.09198/) (2023)
- [RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks](https://mlsanity.com/paper/2307.07840/) (2023)
- [Self-Training with Differentiable Teacher](https://mlsanity.com/paper/2109.07049/) (2021)
- [ifMixup: Interpolating Graph Pair to Regularize Graph Classification](https://mlsanity.com/paper/2110.09344/) (2021)
- [Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2206.05335/) (2022)
- [Network representation learning: A macro and micro view](https://mlsanity.com/paper/2111.10772/) (2021)
- [Counterfactual Adversarial Learning with Representation Interpolation](https://mlsanity.com/paper/2109.04746/) (2021)
- [Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation](https://mlsanity.com/paper/2110.06290/) (2021)
- [LEReg: Empower Graph Neural Networks with Local Energy Regularization](https://mlsanity.com/paper/2203.10565/) (2022)
- [AutoHEnsGNN: Winning Solution to AutoGraph Challenge for KDD Cup 2020](https://mlsanity.com/paper/2111.12952/) (2021)
- [AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange](https://mlsanity.com/paper/2106.05455/) (2021)
- [GPN: A Joint Structural Learning Framework for Graph Neural Networks](https://mlsanity.com/paper/2205.05964/) (2022)
- [Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation](https://mlsanity.com/paper/2304.05749/) (2023)
- [Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification](https://mlsanity.com/paper/2605.20248/) (2026)

## Abstract (arXiv)

We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization. Further, we provide a theoretical analysis of how GraphMix improves the generalization bounds of the underlying graph neural network, without making any assumptions about the "aggregation" layer or the depth of the graph neural networks. We experimentally validate this analysis by applying GraphMix to various architectures such as Graph Convolutional Networks, Graph Attention Networks and Graph-U-Net. Despite its simplicity, we demonstrate that GraphMix can consistently improve or closely match state-of-the-art performance using even simpler architectures such as Graph Convolutional Networks, across three established graph benchmarks: Cora, Citeseer and Pubmed citation network datasets, as well as three newly proposed datasets: Cora-Full, Co-author-CS and Co-author-Physics.