paper-with-me

홈 › Papers

GraphMix: Improved Training of GNNs for Semi-Supervised Learning

2019-09-25 · Vikas Verma, Meng Qu, Kenji Kawaguchi, Alex Lamb, Yoshua Bengio, Juho Kannala, Jian Tang

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.

📄 PDF Abstract BibTeX arXiv:1909.11715

Code (1)

vikasverma1077/GraphMix 공식 구현 pytorch

Tasks

Generalization BoundsGraph AttentionGraph Neural NetworkNode Classification

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음
Graph Convolutional Networks 설명 없음

Similar Papers 제목 키워드 기반

GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning

2019-09-25 · Vikas Verma, Meng Qu, Alex Lamb, Yoshua Bengio 외

We present GraphMix, a regularization technique for Graph Neural Network based semi-supervised object classification, leveraging the recent advances in the regularization of classical deep neural networks. Specifically, …

Graph Neural Network

GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction

2021-06-21 · Lirong Wu, Haitao Lin, Zhangyang Gao, Cheng Tan 외

Recent years have witnessed great success in handling node classification tasks with Graph Neural Networks (GNNs). However, most existing GNNs are based on the assumption that node samples for different classes are balan…

Node Classification

Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning

2020-10-09 · Navid Naderializadeh, Fan H. Hung, Sean Soleyman, Deepak Khosla

We propose a novel framework for value function factorization in multi-agent deep reinforcement learning (MARL) using graph neural networks (GNNs). In particular, we consider the team of agents as the set of nodes of a c…

Deep Reinforcement LearningMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+5

Alternately Optimized Graph Neural Networks

2022-06-08 · Haoyu Han, Xiaorui Liu, Haitao Mao, MohamadAli Torkamani 외

Graph Neural Networks (GNNs) have greatly advanced the semi-supervised node classification task on graphs. The majority of existing GNNs are trained in an end-to-end manner that can be viewed as tackling a bi-level optim…

MULTI-VIEW LEARNINGNode Classification

GraFN: Semi-Supervised Node Classification on Graph with Few Labels via Non-Parametric Distribution Assignment

2022-04-04 · Junseok Lee, Yunhak Oh, Yeonjun In, Namkyeong Lee 외

Despite the success of Graph Neural Networks (GNNs) on various applications, GNNs encounter significant performance degradation when the amount of supervision signals, i.e., number of labeled nodes, is limited, which is …

Node ClassificationSelf-Supervised Learning