Shortest Path Networks for Graph Property Prediction

by   Ralph Abboud, et al.

Most graph neural network models rely on a particular message passing paradigm, where the idea is to iteratively propagate node representations of a graph to each node in the direct neighborhood. While very prominent, this paradigm leads to information propagation bottlenecks, as information is repeatedly compressed at intermediary node representations, which causes loss of information, making it practically impossible to gather meaningful signals from distant nodes. To address this issue, we propose shortest path message passing neural networks, where the node representations of a graph are propagated to each node in the shortest path neighborhoods. In this setting, nodes can directly communicate between each other even if they are not neighbors, breaking the information bottleneck and hence leading to more adequately learned representations. Theoretically, our framework generalizes message passing neural networks, resulting in provably more expressive models. Empirically, we verify the capacity of a basic model of this framework on dedicated synthetic experiments, and on real-world graph classification and regression benchmarks, obtaining several state-of-the-art results.


page 1

page 2

page 3

page 4


Is Rewiring Actually Helpful in Graph Neural Networks?

Graph neural networks compute node representations by performing multipl...

Essentials of Parallel Graph Analytics

We identify the graph data structure, frontiers, operators, an iterative...

Graph Inductive Biases in Transformers without Message Passing

Transformers for graph data are increasingly widely studied and successf...

SP Async:Single Source Shortest Path in Asynchronous Mode on MPI

Finding single source shortest path is a very ubiquitous problem. But wi...

A Neighborhood-preserving Graph Summarization

We introduce in this paper a new summarization method for large graphs. ...

Neural Execution of Graph Algorithms

Graph Neural Networks (GNNs) are a powerful representational tool for so...

Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages

Nowadays, Graph Neural Networks (GNNs) following the Message Passing par...

Please sign up or login with your details

Forgot password? Click here to reset