Two-Level Graph Neural Network

doi:10.1109/TNNLS.2022.3144343

Two-Level Graph Neural Network

2024-04-01

5

OA

AI

DOI：10.1109/TNNLS.2022.3144343

Original

Original request for help

Save

Abstract

En 中文

Graph neural networks (GNNs) are recently proposed neural network structures for the processing of graph-structured data. Due to their employed neighbor aggregation strategy, existing GNNs focus on capturing node-level information and neglect high-level information. Existing GNNs, therefore, suffer from representational limitations caused by the local permutation invariance (LPI) problem. To overcome these limitations and enrich the features captured by GNNs, we propose a novel GNN framework, referred to as the two-level GNN (TL-GNN). This merges subgraph-level information with node-level information. Moreover, we provide a mathematical analysis of the LPI problem, which demonstrates that subgraph-level information is beneficial to overcoming the problems associated with LPI. A subgraph counting method based on the dynamic programming algorithm is also proposed, and this has the time complexity of O(n(3)), where n is the number of nodes of a graph. Experiments show that TL-GNN outperforms existing GNNs and achieves state-of-the-art performance.

Keywords:

Heuristic algorithms

Graph neural networks

Training

Task analysis

Sun

Social networking (online)

Message passing

Attention mechanism

graph neural networks (GNNs)

graph representation

local permutation invariance (LPI)

Two-Level Graph Neural Network

Abstract

Journal

Organization