Advancing Graph Neural Networks with HL-HGAT: A Hodge-Laplacian and Attention Mechanism Approach for Heterogeneous Graph-Structured Data
Authors:
Preprint
Abstract
Graph neural networks (GNNs) have proven effective in capturing relationships among nodes in a graph. This study introduces a novel perspective by considering a graph as a simplicial complex, encompassing nodes, edges, triangles, and $k$-simplices, enabling the definition of graph-structured data on any $k$-simplices. Our contribution is the Hodge-Laplacian heterogeneous graph attention network (HL-HGAT), designed to learn heterogeneous signal representations across $k$-simplices. The HL-HGAT incorporates three key components: HL convolutional filters (HL-filters), simplicial projection (SP), and simplicial attention pooling (SAP) operators, applied to $k$-simplices. HL-filters leverage the unique topology of $k$-simplices encoded by the Hodge-Laplacian (HL) operator, operating within the spectral domain of the $k$-th HL operator. To address computation challenges, we introduce a polynomial approximation for HL-filters, exhibiting spatial localization properties. Additionally, we propose a pooling operator to coarsen $k$-simplices, combining features through simplicial attention mechanisms of self-attention and cross-attention via transformers and SP operators, capturing topological interconnections across multiple dimensions of simplices. The HL-HGAT is comprehensively evaluated across diverse graph applications, including NP-hard problems, graph multi-label and classification challenges, and graph regression tasks in logistics, computer vision, biology, chemistry, and neuroscience. The results demonstrate the model's efficacy and versatility in handling a wide range of graph-based scenarios.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Graph neural network for traffic forecasting: A surveyExpert Systems with Applications, 2022
- Spatio-temporal directed acyclic graph learning with attention mechanisms on brain functional time series and connectivityMedical Image Analysis, 2022
- BrainGNN: Interpretable Brain Graph Neural Network for fMRI AnalysisMedical Image Analysis, 2021
- Revisiting convolutional neural network on graphs with polynomial approximations of Laplace–Beltrami spectral filteringNeural Computing and Applications, 2021
- A compact review of molecular property prediction with graph neural networksDrug Discovery Today: Technologies, 2020
- Spatial temporal incidence dynamic graph neural networks for traffic flow forecastingInformation Sciences, 2020
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- Octanol–water partition coefficient measurements for the SAMPL6 blind prediction challengeJournal of Computer-Aided Molecular Design, 2019
- Hole Detection in Metabolic Connectivity of Alzheimer’s Disease Using k −Laplacian2014
- Technologies for 3D mesh compression: A surveyJournal of Visual Communication and Image Representation, 2005