PF-GNN: Differentiable particle filtering based approximation of universal graph representations

TL;DR

This paper introduces PF-GNN, a differentiable particle filtering approach guiding GNNs with isomorphism techniques to enhance their expressive power for graph representation, outperforming existing models.

Contribution

It proposes a novel, end-to-end differentiable method combining particle filtering with isomorphism solvers to improve GNN expressiveness without high computational costs.

Findings

Outperforms leading GNN models on synthetic isomorphism benchmarks

Achieves better graph discrimination on real-world datasets

Maintains linear runtime increase with improved expressiveness

Abstract

Message passing Graph Neural Networks (GNNs) are known to be limited in expressive power by the 1-WL color-refinement test for graph isomorphism. Other more expressive models either are computationally expensive or need preprocessing to extract structural features from the graph. In this work, we propose to make GNNs universal by guiding the learning process with exact isomorphism solver techniques which operate on the paradigm of Individualization and Refinement (IR), a method to artificially introduce asymmetry and further refine the coloring when 1-WL stops. Isomorphism solvers generate a search tree of colorings whose leaves uniquely identify the graph. However, the tree grows exponentially large and needs hand-crafted pruning techniques which are not desirable from a learning perspective. We take a probabilistic view and approximate the search tree of colorings (i.e. embeddings) by sampling multiple paths from root to leaves of the search tree. To learn more discriminative representations, we guide the sampling process with particle filter updates, a principled approach for sequential state estimation. Our algorithm is end-to-end differentiable, can be applied with any GNN as backbone and learns richer graph representations with only linear increase in runtime. Experimental evaluation shows that our approach consistently outperforms leading GNN models on both synthetic benchmarks for isomorphism detection as well as real-world datasets.