.png){kind=icon}
.png){kind=icon}
Return
Deep positional encoders for graph classification
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2025.112828.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Graph neural networks
Spectral theory
Positional encodings
Graph transformers
Complex network
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.