Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks

By Matthias Fey. 2019

51 citations recorded by the source corpus.

We propose a dynamic neighborhood aggregation (DNA) procedure guided by (multi-head) attention for representation learning on graphs. In contrast to current graph neural networks which follow a simple neighborhood aggregation scheme, our DNA procedure allows for a selective and node-adaptive aggregation of neighboring embeddings of potentially differing locality. In order to avoid overfitting, we propose to control the channel-wise connections between input and output by making use of grouped linear projections. In a number of transductive node-classification experiments, we demonstrate the effectiveness of our approach.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Model Architectures

In Graph Learning

Citations in the corpus

GraphSAINT: Graph Sampling Based Inductive Learning Method (2019, background): “Attention (Veličković et al., 2017; Fey, 2019; Zhang et al., 2018): while explicit variance reduction is hard due to the dynamically updated attention values, it is reasonable to apply attention within the subgraphs which are considered as representatives of the full graph.”
Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View (2019, background): “Fey (2019) allow for a selective and node-adaptive aggregation of the neighboring embeddings of potentially differing locality.”
Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels (2019, result): “[2018], Fey [2019]. In Figure 3, we observe that a similar trend holds for GNTK.”