.png){kind=icon}
返回
Optimizing Graph Neural Network With Multiaspect Hilbert-Schmidt Independence Criterion
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3171419.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The graph neural network (GNN) has demonstrated its superior power in various data mining tasks and has been widely applied in diversified fields. The core of GNN is the aggregation and combination functions, and mainstream GNN studies focus on the enhancement of these functions. However, GNNs face a common challenge, i.e., useless features contained in neighbor nodes may be integrated into the target node during the aggregation process. This leads to poor node embedding and undermines downstream tasks. To tackle this problem, this article proposes a novel GNN optimization framework GNN-MHSIC by introducing the nonparametric dependence method Hilbert-Schmidt independence criterion (HSIC) under the guidance of information bottleneck. HSIC is utilized to guide the information propagation among layers of a GNN from multiaspect views. GNN-MHSIC aims to achieve three main objectives: 1) minimizing the HSIC between the input features and the propagation layers; 2) maximizing the HSIC between the propagation layers and the ground truth; and 3) minimizing the HSIC between the propagation layers. With a multiaspect design, GNN-MHSIC can minimize the propagation of redundant information while preserving relevant information about the target node. We prove GNN-MHSIC's finite upper and lower bounds theoretically and evaluate it experimentally with four classic GNN models, including the graph convolutional network, the graph attention network (GAT), the heterogeneous GAT, and the heterogeneous graph (HG) propagation network on three widely used HGs. The results illustrate the usefulness and performance of GNN-MHSIC.
Keyword:
Optimization
Task analysis
Kernel
Graph neural networks
Random variables
Learning systems
Mutual information
Graph neural network (GNN)
heterogeneous information network (HIN)
Hilbert-Schmidt independence criterion (HSIC)
information bottleneck (IB)
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Formylglycinamide Ribonucleotide Amidotransferase from Thermotoga maritima: Structural Insights into Complex Formation.png)
Biochemistry
OAAI
BiochemistryIF0
OAAI分享收藏The roles of actin cytoskeleton and microtubules for membrane recycling of a food vacuole in Tetrahymena thermophila 嗜热四膜虫 中肌动蛋白细胞骨架和微管在食品液泡膜循环中的作用
PREAI
分享收藏
查看更多内容