DLGNet: Hyperedge Classification through Directed Line Graphs for Chemical Reactions

TL;DR

This paper introduces DLGNet, a spectral graph neural network designed for hypergraph-based chemical reaction classification, leveraging a novel Directed Line Graph Laplacian to encode interaction directionality, resulting in significant performance improvements.

Contribution

The paper presents the first spectral GNN for hypergraphs using the Directed Line Graph transformation and a new Hermitian Laplacian, advancing chemical reaction classification methods.

Findings

DLGNet outperforms existing methods by 33% on average

The Directed Line Graph Laplacian is positive semidefinite and eigen-decomposable

Significant accuracy improvements on real-world chemical datasets

Abstract

Graphs and hypergraphs provide powerful abstractions for modeling interactions among a set of entities of interest and have been attracting a growing interest in the literature thanks to many successful applications in several fields. In particular, they are rapidly expanding in domains such as chemistry and biology, especially in the areas of drug discovery and molecule generation. One of the areas witnessing the fasted growth is the chemical reactions field, where chemical reactions can be naturally encoded as directed hyperedges of a hypergraph. In this paper, we address the chemical reaction classification problem by introducing the notation of a Directed Line Graph (DGL) associated with a given directed hypergraph. On top of it, we build the Directed Line Graph Network (DLGNet), the first spectral-based Graph Neural Network (GNN) expressly designed to operate on a hypergraph via its DLG transformation. The foundation of DLGNet is a novel Hermitian matrix, the Directed Line Graph Laplacian, which compactly encodes the directionality of the interactions taking place within the directed hyperedges of the hypergraph thanks to the DLG representation. The Directed Line Graph Laplacian enjoys many desirable properties, including admitting an eigenvalue decomposition and being positive semidefinite, which make it well-suited for its adoption within a spectral-based GNN. Through extensive experiments on chemical reaction datasets, we show that DGLNet significantly outperforms the existing approaches, achieving on a collection of real-world datasets an average relative-percentage-difference improvement of 33.01%, with a maximum improvement of 37.71%.