Work

Deep positional encoders for graph classification

Year: 2025

Type: article

Abstract: Structural Pattern Recognition (SPR) includes the study of graphs as encoders of non-sequential and permutation-invariant patterns. In this regard, Graph Neural Networks (GNNs) are paving the way towards “inductive SPR” where classical structural problems such as graph classification can be approached through learnable priors. However, since graphs do not have a canonical order, existing GNNs struggle to learn the structural role of each node in the graph, which becomes key in graph classification. In this paper, we address this problem by making Spectral Graph Theory “inductive”, i.e. by learning the eigenvectors of the graph Laplacian, and then using them as positional encoders (PEs). Our experiments show that we improve significantly the SOTA of GNN-based graph classification.

Source: Pattern Recognition

DOI: 10.1016/j.patcog.2025.112828

Authors: Ahmed Begga, Miguel Ángel Lozano, Francisco Escolano

Institution: University of Alicante

Language: English

Topic: Advanced Graph Neural Networks

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $2,590

Funder: Ministerio de Ciencia, Innovación y Universidades