Label Propagation across Graphs: Node Classification using Graph Neural Tangent Kernels

TL;DR

This paper introduces a novel inductive node classification method using graph neural tangent kernels (GNTK) that generalizes across separate graphs without shared connections, leveraging topology and features.

Contribution

It develops a GNTK-based approach with residual connections for inductive graph classification across disjoint graphs, a setting less explored in prior work.

Findings

GNTK with residuals improves classification accuracy.

Method performs well on standard benchmarks.

Effective in inductive, disconnected graph scenarios.

Abstract

Graph neural networks (GNNs) have achieved superior performance on node classification tasks in the last few years. Commonly, this is framed in a transductive semi-supervised learning setup wherein the entire graph, including the target nodes to be labeled, is available for training. Driven in part by scalability, recent works have focused on the inductive case where only the labeled portion of a graph is available for training. In this context, our current work considers a challenging inductive setting where a set of labeled graphs are available for training while the unlabeled target graph is completely separate, i.e., there are no connections between labeled and unlabeled nodes. Under the implicit assumption that the testing and training graphs come from similar distributions, our goal is to develop a labeling function that generalizes to unobserved connectivity structures. To that end, we employ a graph neural tangent kernel (GNTK) that corresponds to infinitely wide GNNs to find correspondences between nodes in different graphs based on both the topology and the node features. We augment the capabilities of the GNTK with residual connections and empirically illustrate its performance gains on standard benchmarks.