Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural NetworksDownload PDF

Published: 31 Oct 2022, Last Modified: 22 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: generalization of graph neural networks, stability, graph metrics
TL;DR: We propose a new graph metric that captures the stability of graph neural networks.
Abstract: Understanding generalization and robustness of machine learning models fundamentally relies on assuming an appropriate metric on the data space. Identifying such a metric is particularly challenging for non-Euclidean data such as graphs. Here, we propose a pseudometric for attributed graphs, the Tree Mover's Distance (TMD), and study its relation to generalization. Via a hierarchical optimal transport problem, TMD reflects the local distribution of node attributes as well as the distribution of local computation trees, which are known to be decisive for the learning behavior of graph neural networks (GNNs). First, we show that TMD captures properties relevant for graph classification: a simple TMD-SVM can perform competitively with standard GNNs. Second, we relate TMD to generalization of GNNs under distribution shifts, and show that it correlates well with performance drop under such shifts.
Supplementary Material: pdf
16 Replies