Learning Structural Node Representation Using Graph Kernels

Registration ID: IJNRD_206426

Published ID: IJNRD2310073

DOI: Click Here to Get

Dr.K.SEKAR , S.LATHA RANI

Structural Learning, Node Representation, graph kernels, structural patterns and graph-structured data

Graphs are a ubiquitous data structure used to represent relationships and dependencies in various domains, including social networks, biology, and recommendation systems. Extracting meaningful representations of nodes within these graphs is essential for tasks such as node classification, link prediction, and community detection. Traditional methods often rely on handcrafted features or heuristics, which may not capture the complex structural patterns present in the data. In this study, we propose a novel approach for learning structural node representations using graph kernels. Graph kernels are powerful tools that quantify the similarity between graphs by comparing their substructures. We extend this concept to capture the structural information of individual nodes within a graph. Our approach leverages graph kernels to generate node embeddings that encode the local and global structural context surrounding each node. To evaluate the effectiveness of our method, we conduct experiments on a diverse set of real-world graph datasets, spanning social networks, biological networks, and citation networks. The results demonstrate that our approach outperforms traditional methods and achieves state-of-the-art performance on various node-centric tasks. Furthermore, we provide insights into the interpretability of the learned node representations, shedding light on the structural patterns and relationships captured by our method. These interpretable representations have the potential to enhance our understanding of graph data and facilitate downstream applications in various domains. In summary, our work introduces a novel framework for learning structural node representations using graph kernels, offering a powerful and interpretable approach for analyzing and extracting valuable insights from graph-structured data. This research contributes to the growing field of graph representation learning and holds promise for a wide range of applications in network analysis, recommendation systems, and beyond.

Published Paper   E-Certificate

Dr.K.SEKAR & S.LATHA RANI (October-2023). Learning Structural Node Representation Using Graph Kernels. INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT, 8(10), a659-a670. https://ijnrd.org/papers/IJNRD2310073.pdf

Volume 8 Issue 10, October-2023

Pages : a659-a670

Paper Reg. ID: IJNRD_206426

Published Paper Id: IJNRD2310073

Downloads: 000122000

Research Area: Engineering

Country: Chennai/Tamil Nadu, TamilNadu, India

Published Paper PDF: https://ijnrd.org/papers/IJNRD2310073.pdf

Published Paper URL: https://ijnrd.org/viewpaperforall?paper=IJNRD2310073

Journal Name: INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT(IJNRD)

ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJNRD (IJ Publication) Janvi Wave | IJNRD.ORG | IJNRD.COM | IJPUB.ORG

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition

Call For Paper - Volume 10 | Issue 10 | October 2025

IJNRD is a Scholarly Open Access, Peer-reviewed, and Refereed Journal with a High Impact Factor of 8.76 (calculated by Google Scholar & Semantic Scholar | AI-Powered Research Tool). It is a Multidisciplinary, Monthly, Low-Cost Journal that follows UGC CARE 2025 Peer-Reviewed Journal Policy norms, Scopus journal standards, and Transparent Peer Review practices to ensure quality and credibility. IJNRD provides indexing in all major databases & metadata repositories, a citation generator, and Digital Object Identifier (DOI) for every published article with full open-access visibility.

The INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (IJNRD) aims to advance applied, theoretical, and experimental research across diverse fields. Its goal is to promote global scientific information exchange among researchers, developers, engineers, academicians, and practitioners. IJNRD serves as a platform where educators and professionals can share research evidence, models of best practice, and innovative ideas, contributing to academic growth and industry relevance.

Indexing Coverage includes Google Scholar, SSRN, ResearcherID-Publons, Semantic Scholar (AI-Powered Research Tool), Microsoft Academic, Academia.edu, arXiv.org, ResearchGate, CiteSeerX, ResearcherID (Thomson Reuters), Mendeley, DocStoc, ISSUU, Scribd, and many more recognized academic repositories.

How to submit the paper?

By Our website

Click Here to Submit Paper Online

By Mail

Send your paper to editor@ijnrd.org

Important Dates for Current issue

Paper Submission Open For: October 2025

Current Issue: Volume 10 | Issue 10 | October 2025

Impact Factor: 8.76

Last Date for Paper Submission: Till 31-Oct-2025

Notification of Review Result: Within 1-2 Days after Submitting paper.

Publication of Paper: Within 01-02 Days after Submititng documents.

Frequency: Monthly (12 issue Annually).

Journal Type: IJNRD is an International Peer-reviewed, Refereed, and Open Access Journal with Transparent Peer Review as per the new UGC CARE 2025 guidelines, offering low-cost multidisciplinary publication with Crossref DOI and global indexing.

Subject Category: Research Area

Call for Paper: More Details