Representation Learning on Graphs with Jumping Knowledge Networks

Code

• github.com/xnuohz/jknet-dgl
  pytorch★ 0
• github.com/dmlc/dgl/tree/master/examples/pytorch/jknet
  pytorch★ 0
• github.com/willy-b/tiny-GIN-for-ogbg-molhiv
  pytorch★ 0
• github.com/mori97/JKNet-dgl
  pytorch★ 0
• github.com/shinkyuy/representation_learning_on_graphs_with_jumping_knowledge_networks
  none★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions