Representation Learning on Graphs with Jumping Knowledge Networks

06/09/2018
by   Keyulu Xu, et al.
0

Recent deep learning approaches for representation learning on graphs follow a neighborhood aggregation procedure. We analyze some important properties of these models, and propose a strategy to overcome those. In particular, the range of "neighboring" nodes that a node's representation draws from strongly depends on the graph structure, analogous to the spread of a random walk. To adapt to local neighborhood properties and tasks, we explore an architecture -- jumping knowledge (JK) networks -- that flexibly leverages, for each node, different neighborhood ranges to enable better structure-aware representation. In a number of experiments on social, bioinformatics and citation networks, we demonstrate that our model achieves state-of-the-art performance. Furthermore, combining the JK framework with models like Graph Convolutional Networks, GraphSAGE and Graph Attention Networks consistently improves those models' performance.

READ FULL TEXT

page 4

page 5

page 6

page 12

page 13

page 14

05/21/2019

Neighborhood Enlargement in Graph Neural Networks

Graph Neural Network (GNN) is an effective framework for representation ...
01/02/2021

Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network

Graphs are often used to organize data because of their simple topologic...
04/09/2019

Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks

We propose a dynamic neighborhood aggregation (DNA) procedure guided by ...
08/27/2021

Using Graph Neural Networks to model the performance of Deep Neural Networks

With the unprecedented proliferation of machine learning software, there...
11/05/2019

GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction

Graph representation learning is of paramount importance for a variety o...
06/06/2020

Are Graph Convolutional Networks Fully Exploiting Graph Structure?

Graph Convolutional Networks (GCNs) generalize the idea of deep convolut...
02/14/2018

Graph2Seq: Scalable Learning Dynamics for Graphs

Neural networks have been shown to be an effective tool for learning alg...