Representation Learning on Graphs with Jumping Knowledge Networks

by   Keyulu Xu, et al.

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.


page 4

page 5

page 6

page 12

page 13

page 14


Neighborhood Enlargement in Graph Neural Networks

Graph Neural Network (GNN) is an effective framework for representation ...

Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network

Graphs are often used to organize data because of their simple topologic...

Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks

We propose a dynamic neighborhood aggregation (DNA) procedure guided by ...

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

With the unprecedented proliferation of machine learning software, there...

GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction

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

Are Graph Convolutional Networks Fully Exploiting Graph Structure?

Graph Convolutional Networks (GCNs) generalize the idea of deep convolut...

Graph2Seq: Scalable Learning Dynamics for Graphs

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