| 摘要: |
| 近年来,将卷积神经网络推广到图数据上的图卷积神经网络引起了广泛关注,主要包括重新定义图的卷积和池化操作.由于图数据只能表达二元关系的局限性,使其在实际应用中表现欠佳.相比之下,超图能够捕获数据的高阶相关性,利用其灵活的超边易于处理复杂的数据表示.然而,现有的超图卷积神经网络还不够成熟,目前尚无有效的超图池化操作.因此,提出了带有自注意机制的超图池化网络,使用超图结构建模,通过引入自注意力的超图卷积操作学习带有高阶数据信息的节点隐藏层特征,再经过超图池化操作选择并保留在结构和内容上的重要节点,进而得到更准确的超图表示.在文本分类、菜肴分类和蛋白质分类任务上的实验结果表明:与目前多种主流方法相比,该方法均取得了更好的效果. |
| 关键词: 超图 卷积神经网络 池化 图神经网络 超图神经网络 |
| DOI：10.13328/j.cnki.jos.006881 |
| 分类号: |
| 基金项目:国家重点研发计划(2020AAA0108503);国家自然科学基金(62272045) |
|
| Self-attention Hypergraph Pooling Network |
|
ZHAO Ying-Fu, JIN Fu-Sheng, LI Rong-Hua, QIN Hong-Chao, CUI Peng, WANG Guo-Ren
|
|
School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China
|
| Abstract: |
| Recently, graph-based convolutional neural networks (GCNs) have attracted much attention by generalizing convolutional neural networks to graph data, which includes redefining the convolution and the pooling operations on graphs. Due to the limitation that graph data can only focus on dyadic relations, it cannot perform well in real practice. In contrast, a hypergraph can capture high-order data interaction and is easy to deal with complex data representation using its flexible hyperedges. Nevertheless, the existing methods for hypergraph convolutional networks are still not mature, currently there is no effective operation for hypergraph pooling. Therefore, a hypergraph pooling network with self-attention mechanism is proposed. Using hypergraph structure for data modeling, this model can learn hidden node features with high-order data information through hyper-convolution operation which introduces self-attention mechanism, select important nodes both on structure and content through hyper-pooling operation, and then obtain more accurate hypergraph representation. Experiments on text classification, dish classification, and protein classification tasks show that the proposed method outperforms recent state-of-the art methods. |
| Key words: hypergraph convolutional neural network pooling graph neural network hypergraph neural network |
