This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
Last revision Both sides next revision
pointer_network [2017/07/14 11:10] external edit
pointer_network [2018/09/08 11:43]
Line 48: Line 48:
 http://​fastml.com/​introduction-to-pointer-networks/​ http://​fastml.com/​introduction-to-pointer-networks/​
 +https://​arxiv.org/​pdf/​1806.08804.pdf Hierarchical Graph Representation Learning with Differentiable Pooling
 +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
 +https://​arxiv.org/​abs/​1809.01797 Narrating a Knowledge Base