Encoder embedding for general graph and node classification

Abstract Graph encoder embedding, a recent technique for graph data, offers speed and scalability in producing vertex-level representations from binary graphs. In this paper, we extend the applicability of this method to a general graph model, which includes weighted graphs, distance matrices, and k...

Full description

Saved in:
Bibliographic Details
Main Author: Cencheng Shen
Format: Article
Language:English
Published: SpringerOpen 2024-10-01
Series:Applied Network Science
Subjects:
Online Access:https://doi.org/10.1007/s41109-024-00678-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203795773980672
author Cencheng Shen
author_facet Cencheng Shen
author_sort Cencheng Shen
collection DOAJ
description Abstract Graph encoder embedding, a recent technique for graph data, offers speed and scalability in producing vertex-level representations from binary graphs. In this paper, we extend the applicability of this method to a general graph model, which includes weighted graphs, distance matrices, and kernel matrices. We prove that the encoder embedding satisfies the law of large numbers and the central limit theorem on a per-observation basis. Under certain condition, it achieves asymptotic normality on a per-class basis, enabling optimal classification through discriminant analysis. These theoretical findings are validated through a series of experiments involving weighted graphs, as well as text and image data transformed into general graph representations using appropriate distance metrics.
format Article
id doaj-art-33afcf04b0804afd8f9fa9ed8ee3f50b
institution OA Journals
issn 2364-8228
language English
publishDate 2024-10-01
publisher SpringerOpen
record_format Article
series Applied Network Science
spelling doaj-art-33afcf04b0804afd8f9fa9ed8ee3f50b2025-08-20T02:11:25ZengSpringerOpenApplied Network Science2364-82282024-10-019111710.1007/s41109-024-00678-4Encoder embedding for general graph and node classificationCencheng Shen0Department of Applied Economics and Statistics, University of DelawareAbstract Graph encoder embedding, a recent technique for graph data, offers speed and scalability in producing vertex-level representations from binary graphs. In this paper, we extend the applicability of this method to a general graph model, which includes weighted graphs, distance matrices, and kernel matrices. We prove that the encoder embedding satisfies the law of large numbers and the central limit theorem on a per-observation basis. Under certain condition, it achieves asymptotic normality on a per-class basis, enabling optimal classification through discriminant analysis. These theoretical findings are validated through a series of experiments involving weighted graphs, as well as text and image data transformed into general graph representations using appropriate distance metrics.https://doi.org/10.1007/s41109-024-00678-4Graph embeddingGeneral graphAsymptotic theory
spellingShingle Cencheng Shen
Encoder embedding for general graph and node classification
Applied Network Science
Graph embedding
General graph
Asymptotic theory
title Encoder embedding for general graph and node classification
title_full Encoder embedding for general graph and node classification
title_fullStr Encoder embedding for general graph and node classification
title_full_unstemmed Encoder embedding for general graph and node classification
title_short Encoder embedding for general graph and node classification
title_sort encoder embedding for general graph and node classification
topic Graph embedding
General graph
Asymptotic theory
url https://doi.org/10.1007/s41109-024-00678-4
work_keys_str_mv AT cenchengshen encoderembeddingforgeneralgraphandnodeclassification