Local Vertex Colouring Graph Neural Networks
This work addresses expressivity bottlenecks in GNNs for graph learning tasks, offering a novel method that is incremental in improving efficiency and applicability.
The authors tackled the problem of limited expressivity in Graph Neural Networks (GNNs) beyond the Weisfeiler-Lehman framework by proposing a new vertex coloring scheme based on graph search, which efficiently extends expressivity and helps solve problems like graph biconnectivity, with expressivity increasing hierarchically under certain conditions.
In recent years, there has been a significant amount of research focused on expanding the expressivity of Graph Neural Networks (GNNs) beyond the Weisfeiler-Lehman (1-WL) framework. While many of these studies have yielded advancements in expressivity, they have frequently come at the expense of decreased efficiency or have been restricted to specific types of graphs. In this study, we investigate the expressivity of GNNs from the perspective of graph search. Specifically, we propose a new vertex colouring scheme and demonstrate that classical search algorithms can efficiently compute graph representations that extend beyond the 1-WL. We show the colouring scheme inherits useful properties from graph search that can help solve problems like graph biconnectivity. Furthermore, we show that under certain conditions, the expressivity of GNNs increases hierarchically with the radius of the search neighbourhood. To further investigate the proposed scheme, we develop a new type of GNN based on two search strategies, breadth-first search and depth-first search, highlighting the graph properties they can capture on top of 1-WL. Our code is available at https://github.com/seanli3/lvc.