Representation Learning on Graphs with Jumping Knowledge Networks
This work solves the issue of structure-aware representation learning for graph-based tasks, offering incremental improvements to existing methods.
The authors tackled the problem of graph representation learning by addressing the dependence of node representations on graph structure, proposing jumping knowledge networks to adaptively leverage different neighborhood ranges. Their model achieved state-of-the-art performance on social, bioinformatics, and citation networks, and consistently improved existing models like Graph Convolutional Networks when combined.
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.