.png){kind=icon}
返回
Multi-view graph imputation network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.inffus.2023.102024.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph data in the real world is often accompanied by the problem of missing attributes. Recently, self-supervised graph representation learning, implementing data imputation according to observable nodes, has become a paradigm for studying attribute-missing graphs. However, existing methods directly encode attribute-missing graphs and then impute attribute-missing nodes in the latent space, which often increases the uncertainty of node embedding information, thereby limiting the performance of attribute imputation. To address this issue, we propose a novel method named Multi-view GrAph impuTation nEtwork (MATE), which performs attribute imputation in the input space for attribute-missing graphs. Specifically, we first employ parameter initialization and graph diffusion in the input space to generate relatively complete multi-view from both the attribute and structure levels. To provide reliable guidance in each epoch for parameter initialization, we propose a Dual Constraint Strategy (DCS) that maximizes the consistency of node embeddings between two views. In this way, the learning of parameter initialization and node embedding promotes each other, thus effectively improving the quality of attribute imputation. Extensive experiments on four benchmark datasets demonstrate that our proposed MATE achieves state-of-the-art performance. The corresponding code is available at https://github.com/XinPeng97/MATE.
Keyword:
Multi-view learning
Attribute-missing graph
Graph auto-encoder
Self-supervised learning
Graph representation learning
期刊
IF:
15.5
论文数:
4.2K
被引数:
2.7W
机构
引用论文
分享收藏An Increased Lateral Femoral Condyle Ratio Is a Risk Factor for Anterior Cruciate Ligament Injury
PREAI
分享收藏Local2Global: Unsupervised multi-view deep graph representation learning with Nearest Neighbor ConstraintLocal2Global: 具有最近邻约束的无监督多视图深度图表示学习
PREAI
分享收藏Missing data imputation with adversarially-trained graph convolutional networks使用敌方训练的图卷积网络进行缺失数据插补.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏
Protein deep profile and model predictions for identifying the causal genes of male infertility based on deep learningINFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏Hybrid deep learning models for traffic prediction in large-scale road networks大规模路网交通预测的混合深度学习模型INFORMATION FUSIONOAAI
INFORMATION FUSIONIF15.5
OAAI分享收藏
查看更多内容