Graph Attention Networks
Graph Attention Networks
复制标题
DOI：
10.17863/cam.48429
复制
发表时间：
2017-10
期刊：
影响因子：
--
通讯作者：
Petar Velickovic;Guillem Cucurull;Arantxa Casanova;Adriana Romero;P. Lio’;Yoshua Bengio
中科院分区：
文献类型：
--
作者：
Petar Velickovic;Guillem Cucurull;Arantxa Casanova;Adriana Romero;P. Lio’;Yoshua Bengio
我们提出了图注意网络（GATs），这是一种新颖的神经网络架构，可以在图结构数据上运行，利用隐藏的自注意层来解决基于图卷积或其近似的先前方法的缺点。通过堆叠层，其中的节点能够参与其邻居的特征，我们可以（隐式地）为邻居中的不同节点指定不同的权重，而不需要任何昂贵的矩阵操作（例如反转）或依赖于预先知道的图结构。通过这种方式，我们同时解决了基于频谱的图神经网络的几个关键挑战，并使我们的模型很容易适用于感应和转导问题。我们的GAT模型已经在四个已建立的传导和归纳图基准中达到或匹配了最先进的结果：Cora， Citeseer和Pubmed引文网络数据集，以及蛋白质-蛋白质相互作用数据集（其中测试图在训练期间保持不可见）。
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).