Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/159273
Title: SGAT: simplicial Graph attention network
Authors: Lee, See Hian
Ji, Feng 
Tay, Wee Peng
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Issue Date: 2022
Source: Lee, S. H., Ji, F. & Tay, W. P. (2022). SGAT: simplicial Graph attention network. Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22), 3192-3200.
Project: MOE-T2EP20220-0002 
Conference: Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22)
Abstract: Heterogeneous graphs have multiple node and edge types and are semantically richer than homogeneous graphs. To learn such complex semantics, many graph neural network approaches for heterogeneous graphs use metapaths to capture multi-hop interactions between nodes. Typically, features from non-target nodes are not incorporated into the learning procedure. However, there can be nonlinear, high-order interactions involving multiple nodes or edges. In this paper, we present Simplicial Graph Attention Network (SGAT), a simplicial complex approach to represent such high-order interactions by placing features from non-target nodes on the simplices. We then use attention mechanisms and upper adjacencies to generate representations. We empirically demonstrate the efficacy of our approach with node classification tasks on heterogeneous graph datasets and further show SGAT's ability in extracting structural information by employing random node features. Numerical experiments indicate that SGAT performs better than other current state-of-the-art heterogeneous graph learning methods.
URI: https://hdl.handle.net/10356/159273
URL: https://www.ijcai.org/proceedings/2022/
ISBN: 978-1-956792-00-3
Schools: School of Electrical and Electronic Engineering 
Rights: © 2022 International Joint Conferences on Artificial Intelligence. All rights reserved. This paper was published in Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22) and is made available with permission of International Joint Conferences on Artificial Intelligence.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Conference Papers

Files in This Item:
File Description SizeFormat 
IJCAI__22_SGAT (1).pdf492.21 kBAdobe PDFThumbnail
View/Open

Page view(s)

107
Updated on Feb 28, 2024

Download(s) 50

27
Updated on Feb 28, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.