The Surprising Behavior Of Graph Neural Networks

25 Sep 2019  ·  Vivek Kothari, Catherine Tong, Nicholas Lane ·

We highlight a lack of understanding of the behaviour of Graph Neural Networks (GNNs) in various topological contexts. We present 4 experimental studies which counter-intuitively demonstrate that the performance of GNNs is weakly dependent on the topology, sensitive to structural noise and the modality (attributes or edges) of information, and degraded by strong coupling between nodal attributes and structure. We draw on the empirical results to recommend reporting of topological context in GNN evaluation and propose a simple (attribute-structure) decoupling method to improve GNN performance.

PDF Abstract
No code implementations yet. Submit your code now

Tasks


Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here