.png){kind=icon}
返回
Learnable Graph Convolutional Network With Semisupervised Graph Information Bottleneck
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2023.3322739.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph convolutional network (GCN) has gained widespread attention in semisupervised classification tasks. Recent studies show that GCN-based methods have achieved decent performance in numerous fields. However, most of the existing methods generally adopted a fixed graph that cannot dynamically capture both local and global relationships. This is because the hidden and important relationships may not be directed exhibited in the fixed structure, causing the degraded performance of semisupervised classification tasks. Moreover, the missing and noisy data yielded by the fixed graph may result in wrong connections, thereby disturbing the representation learning process. To cope with these issues, this article proposes a learnable GCN-based framework, aiming to obtain the optimal graph structures by jointly integrating graph learning and feature propagation in a unified network. Besides, to capture the optimal graph representations, this article designs dual-GCN-based meta-channels to simultaneously explore local and global relations during the training process. To minimize the interference of the noisy data, a semisupervised graph information bottleneck (SGIB) is introduced to conduct the graph structural learning (GSL) for acquiring the minimal sufficient representations. Concretely, SGIB aims to maximize the mutual information of both the same and different meta-channels by designing the constraints between them, thereby improving the node classification performance in the downstream tasks. Extensive experimental results on real-world datasets demonstrate the robustness of the proposed model, which outperforms state-of-the-art methods with fixed-structure graphs.
Keyword:
Graph convolutional network (GCN)
graph information bottleneck
graph learning
mutual information
semisupervised learning
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Oscillatory activity is not evident in the primate temporal visual cortex with static stimuli.png)
NeuroReport
NeuroReportIF0
PREAI
分享收藏AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-SmoothingAGNN: 缓解过度平滑的交替图正则化神经网络
OAAI
OAAI分享收藏Deep Feature Aggregation Framework Driven by Graph Convolutional Network for Scene Classification in Remote Sensing图卷积网络驱动的遥感场景深度特征聚合框架
PREAI
分享收藏
查看更多内容