.png){kind=icon}
返回
NCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classification
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2022.3179306.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Message passing has evolved as an effective tool for designing graph neural networks (GNNs). However, most existing methods for message passing simply sum or average all the neighboring features to update node representations. They are restricted by two problems: 1) lack of interpretability to identify node features significant to the prediction of GNNs and 2) feature overmixing that leads to the oversmoothing issue in capturing long-range dependencies and inability to handle graphs under heterophily or low homophily. In this article, we propose a node-level capsule graph neural network (NCGNN) to address these problems with an improved message passing scheme. Specifically, NCGNN represents nodes as groups of node-level capsules, in which each capsule extracts distinctive features of its corresponding node. For each node-level capsule, a novel dynamic routing procedure is developed to adaptively select appropriate capsules for aggregation from a subgraph identified by the designed graph filter. NCGNN aggregates only the advantageous capsules and restrains irrelevant messages to avoid overmixing features of interacting nodes. Therefore, it can relieve the oversmoothing issue and learn effective node representations over graphs with homophily or heterophily. Furthermore, our proposed message passing scheme is inherently interpretable and exempt from complex post hoc explanations, as the graph filter and the dynamic routing procedure identify a subset of node features that are most significant to the model prediction from the extracted subgraph. Extensive experiments on synthetic as well as real-world graphs demonstrate that NCGNN can well address the oversmoothing issue and produce better node representations for semisupervised node classification. It outperforms the state of the arts under both homophily and heterophily.
Keyword:
Message passing
Routing
Graph neural networks
Feature extraction
Predictive models
Task analysis
Aggregates
Capsule
graph neural networks (GNNs)
homophily and heterophily
message passing
oversmoothing
semisupervised classification
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
分享收藏Conjugated heat transfer and temperature distributions in a gas turbine combustion liner under base-load operation基本负荷运行下燃气轮机燃烧衬里中的共轭传热和温度分布
PREAI
分享收藏Nonsingular Terminal Sliding Mode Control Based on Adaptive Barrier Function for nth-Order Perturbed Nonlinear Systems.png)
MathematicsOAAI
MathematicsIF0
OAAI分享收藏Therapeutic Antagonism Between Anticholinergics and Neuroleptics: Possible Involvement of Cholinergic Mechanisms in Schizophrenia抗胆碱能药和抗精神病药之间的治疗拮抗作用: 精神分裂症中胆碱能机制的可能参与
OAAI
OAAI分享收藏
查看更多内容