Template based Graph Neural Network with Optimal Transport Distances

by   Cédric Vincent-Cuaz, et al.

Current Graph Neural Networks (GNN) architectures generally rely on two important components: node features embedding through message passing, and aggregation with a specialized form of pooling. The structural (or topological) information is implicitly taken into account in these two steps. We propose in this work a novel point of view, which places distances to some learnable graph templates at the core of the graph representation. This distance embedding is constructed thanks to an optimal transport distance: the Fused Gromov-Wasserstein (FGW) distance, which encodes simultaneously feature and structure dissimilarities by solving a soft graph-matching problem. We postulate that the vector of FGW distances to a set of template graphs has a strong discriminative power, which is then fed to a non-linear classifier for final predictions. Distance embedding can be seen as a new layer, and can leverage on existing message passing techniques to promote sensible feature representations. Interestingly enough, in our work the optimal set of template graphs is also learnt in an end-to-end fashion by differentiating through this layer. After describing the corresponding learning procedure, we empirically validate our claim on several synthetic and real life graph classification datasets, where our method is competitive or surpasses kernel and GNN state-of-the-art approaches. We complete our experiments by an ablation study and a sensitivity analysis to parameters.


page 1

page 2

page 3

page 4


Optimal Transport Graph Neural Networks

Current graph neural network (GNN) architectures naively average or sum ...

On a linear fused Gromov-Wasserstein distance for graph structured data

We present a framework for embedding graph structured data into a vector...

Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities

Graph neural networks (GNNs) have been widely used to learn vector repre...

Domain-adaptive Message Passing Graph Neural Network

Cross-network node classification (CNNC), which aims to classify nodes i...

Directional Message Passing on Molecular Graphs via Synthetic Coordinates

Graph neural networks that leverage coordinates via directional message ...

Neural Execution of Graph Algorithms

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

The Weisfeiler-Lehman Distance: Reinterpretation and Connection with GNNs

In this paper, we present a novel interpretation of the so-called Weisfe...

Please sign up or login with your details

Forgot password? Click here to reset