2019/09/25 by Vikas Verma, Meng Qu, Verma, Vikas +11 · 2 citations
Computer Science · Mathematics · #Advanced Graph Neural Networks #Artificial intelligence #Artificial neural network #Computer science #Convolutional neural network #FOS: Computer and information sciences #Graph #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Healthcare #Machine learning #Regularization (linguistics) #Theoretical computer science #Topic Modeling #cs.LG #stat.ML
paper · pdf · open access · doi:10.48550/arxiv.1909.11715
published in arXiv (Cornell University) (Cornell University) · https://github.com/vikasverma1077/GraphMix
openalex publication_date 2019/09/25 · arxiv created 2020/10/08 · arxiv updated 2020/10/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.