Hierarchical Graph Representation Learning with Differentiable Pooling
Hierarchical Graph Representation Learning with Differentiable Pooling
复制标题
DOI：
--
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
Rex Ying;Jiaxuan You;Christopher Morris;Xiang Ren;William L. Hamilton;J. Leskovec
中科院分区：
文献类型：
--
作者：
Rex Ying;Jiaxuan You;Christopher Morris;Xiang Ren;William L. Hamilton;J. Leskovec
最近，图神经网络（GNN）通过有效学习节点嵌入，彻底改变了图表示学习领域，并在节点分类和链接预测等任务中取得了最先进的成果。然而，目前的GNN方法本质上是平坦的，并且不学习图的分层表示-这一限制对于图分类任务来说尤其成问题，其中目标是预测与整个图相关联的标签。在这里，我们提出了DiffPool，这是一个可微分图池化模块，可以生成图的分层表示，并且可以以端到端的方式与各种图神经网络架构相结合。DiffPool为深度GNN的每一层的节点学习可区分的软集群分配，将节点映射到一组集群，然后形成下一个GNN层的粗化输入。我们的实验结果表明，与所有现有的池化方法相比，将现有的GNN方法与DiffPool相结合，在图分类基准上平均提高了5-10%的准确率，在五个基准数据集中的四个上实现了新的最先进水平。
Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings, and achieved state-of-the-art results in tasks such as node classification and link prediction. However, current GNN methods are inherently flat and do not learn hierarchical representations of graphs---a limitation that is especially problematic for the task of graph classification, where the goal is to predict the label associated with an entire graph. Here we propose DiffPool, a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion. DiffPool learns a differentiable soft cluster assignment for nodes at each layer of a deep GNN, mapping nodes to a set of clusters, which then form the coarsened input for the next GNN layer. Our experimental results show that combining existing GNN methods with DiffPool yields an average improvement of 5-10% accuracy on graph classification benchmarks, compared to all existing pooling approaches, achieving a new state-of-the-art on four out of five benchmark datasets.