超图
稳健性(进化)
计算机科学
卷积(计算机科学)
编码
图形
顶点(图论)
理论计算机科学
人工智能
人工神经网络
模式识别(心理学)
数学
离散数学
生物化学
基因
化学
作者
Jianwen Jiang,Yuxuan Wei,Yifan Feng,Jingxuan Cao,Yue Gao
标识
DOI:10.24963/ijcai.2019/366
摘要
In recent years, graph/hypergraph-based deep learning methods have attracted much attention from researchers. These deep learning methods take graph/hypergraph structure as prior knowledge in the model. However, hidden and important relations are not directly represented in the inherent structure. To tackle this issue, we propose a dynamic hypergraph neural networks framework (DHGNN), which is composed of the stacked layers of two modules: dynamic hypergraph construction (DHG) and hypergrpah convolution (HGC). Considering initially constructed hypergraph is probably not a suitable representation for data, the DHG module dynamically updates hypergraph structure on each layer. Then hypergraph convolution is introduced to encode high-order data relations in a hypergraph structure. The HGC module includes two phases: vertex convolution and hyperedge convolution, which are designed to aggregate feature among vertices and hyperedges, respectively. We have evaluated our method on standard datasets, the Cora citation network and Microblog dataset. Our method outperforms state-of-the-art methods. More experiments are conducted to demonstrate the effectiveness and robustness of our method to diverse data distributions.
科研通智能强力驱动
Strongly Powered by AbleSci AI