Graph U-Nets
Graph U-Nets
复制标题
DOI：
10.1109/tpami.2021.3081010
复制
发表时间：
2022-09-01
影响因子：
23.6
通讯作者：
Ji, Shuiwang
中科院分区：
文献类型：
--
作者：
Gao, Hongyang;Ji, Shuiwang
我们考虑了图数据的表示学习问题。鉴于图像是节点位于二维网格上的图的特殊情况，图嵌入任务与图像像素预测任务（如分割）具有天然的对应关系。虽然像U-Nets这样的编码器-解码器架构已经成功地应用于图像像素预测任务，但对于图形数据却缺乏类似的方法。这是因为池化和上采样操作在图数据上并不自然。为了解决这些挑战，我们提出了新的图池化和解池化操作。gPool层根据节点的标量投影值自适应选择节点组成较小的图。我们进一步提出gUnpool层作为gPool层的逆操作。基于我们提出的方法，我们开发了一个编码器-解码器模型，称为图U-Nets。在节点分类和图分类任务上的实验结果表明，我们的方法始终比以前的模型具有更好的性能。沿着这个方向，我们通过整合注意力机制来扩展我们的方法。在注意算子的基础上，提出了基于注意的池化和解池化层，可以更好地捕获图的拓扑信息。在图分类任务上的实证结果证明了我们的方法具有良好的性能。
We consider the problem of representation learning for graph data. Given images are special cases of graphs with nodes lie on 2D lattices, graph embedding tasks have a natural correspondence with image pixel-wise prediction tasks such as segmentation. While encoder-decoder architectures like U-Nets have been successfully applied to image pixel-wise prediction tasks, similar methods are lacking for graph data. This is because pooling and up-sampling operations are not natural on graph data. To address these challenges, we propose novel graph pooling and unpooling operations. The gPool layer adaptively selects some nodes to form a smaller graph based on their scalar projection values. We further propose the gUnpool layer as the inverse operation of the gPool layer. Based on our proposed methods, we develop an encoder-decoder model, known as the graph U-Nets. Experimental results on node classification and graph classification tasks demonstrate that our methods achieve consistently better performance than previous models. Along this direction, we extend our methods by integrating attention mechanisms. Based on attention operators, we proposed attention-based pooling and unpooling layers, which can better capture graph topology information. The empirical results on graph classification tasks demonstrate the promising capability of our methods.