Concepts And Techniques Of Graph Neural Networks – Vinod Kumar

Common Neighbors – Simple and intuitive – Computationally efficient – May not work well for sparse networks – Ignores the strength of connections between nodes Liben-Nowell, D., & Kleinberg, J. (2007). The link prediction problem for social networks. Journal of the American Society for Information Science and Technology. Jaccard Coefficient – Simple and intuitive – Computationally efficient – May not work well for sparse networks – Ignores the strength of connections between nodes Liben-Nowell, D., & Kleinberg, J.

(2007). The link prediction problem for social networks. Journal of the American Society for Information Science and Technology. Adamic-Adar Index – Considers the importance of common – May not work well for sparse networks Adamic, L. A., & Adar, E. (2003). Friends and neighbors – Computationally efficient – Ignores the strength of connections between nodes neighbors on the Web. Social Networks. Preferential Attachment – Considers the importance of node degree – Computationally efficient – May not work well for networks with strong community structure – Ignores the strength of connections between nodes Barabási, A.

L., & Albert, R. (1999). Emergence of scaling in random networks. Science. Random Walk with Restart – Can handle directed and weighted networks – Can consider multiple features of nodes and edges – Computationally expensive for large-scale networks – May require tuning of parameters Tong, Faloutsos, C., & Pan, J. Y. (2006). Fast random walk with restart and its applications.

Transactions on Knowledge and Data Engineering. Deep Learning Models – Can handle large and complex networks – Require large amounts of data for training Hamilton, Ying, & Leskovec, (2017). – Can consider multiple types of features – Can capture non-linear relationships – Computationally expensive Representation learning on graphs: Methods and applications. Data Engineering Bulletin. APPLICATIONS OF GCNNs FOR LINK GCNNs have proven to be effective in predicting links in social networks due to their ability to model intricate node interactions and capture complex network structures.

The following are some examples of GCNN applications for link prediction in social networks: 1. Recommender Systems: GCNNs have been used in recommender systems to predict links between users and items. For example, a study by Ying et al. (2018) used GCNNs to model user-item interactions in the MovieLens dataset, achieving state-of-the-art performance in recommendation accuracy.

2. Social Media Analysis: The use of GCNNs has been implemented for predicting links within social media networks, including Facebook and Twitter. One instance is a research conducted by Kipf and Welling in 2017, which utilized GCNNs to forecast retweeting actions on Twitter.

Published in the United States of America by IGI Global (an imprint of IGI Global) 701 E. Chocolate Avenue Hershey PA 17033 Tel: 717-533-8845 Fax: 717-533-8661 E-mail: [email protected] Web site: http://www.igi- global.com/reference Copyright © 2023 by IGI Global. All rights reserved. No part of this publication may be reproduced, stored or distributed in any form or by any means, electronic or mechanical, including photocopying, without written permission from the publisher.

Product or company names used in this set are for identification purposes only. Inclusion of the names of the products or companies does not indicate a claim of ownership by IGI Global of the trademark or registered trademark. Library of Congress Cataloging-in-Publication Data Names: Kumar, Vinod, 1986- editor. | Rajput, Dharmendra Singh, 1985- editor.

Title: Concepts and techniques of graph neural network / edited by Vinod Kumar, Dharmendra Singh Rajput. Description: Hershey, PA : Engineering Science Reference, [2023] | Includes bibliographical references and index. | Summary: “This book will aim to provide stepwise discussion; exhaustive literature review; detailed analysis and discussion; rigorous experimentation results, application-oriented approach that will be demonstrated with respect to applications of Graph Neural Network (GNN).

It will be written to develop the understanding of concepts and techniques on GNN and to establish the familiarity of different real applications in various domains for GNN. Moreover, it will also cover the prevailing challenges and opportunities”– Provided by publisher. Identifiers: LCCN 2022052611 (print) | LCCN 2022052612 (ebook) | ISBN 9781668469033 (hardcover) | ISBN 9781668469040 (paperback) | ISBN 9781668469057 (ebook) Subjects: LCSH: Neural networks (Computer science) | Graph theory–Data processing.

Classification: LCC QA76.87 .C66555 2023 (print) | LCC QA76.87 (ebook) | DDC 006.3/2–dc23/eng/20221207 LC record available at https://lccn.loc.gov/2022052611 LC ebook record available at https://lccn.loc.gov/2022052612 This book is published under the IGI Global book series Advances in Systems Analysis, Software Engineering, and High Performance Computing (ASASEHPC) (ISSN: 2327-3453 eISSN: 2327-3461) British Cataloguing in Publication Data A Cataloguing in Publication record for this book is available from the British Library.

All work contributed to this book is new, previously-unpublished material. The views expressed in this book are those of the authors, but not necessarily of the publisher.

This is a short excerpt from the opening of “” by Unknown, quoted for review and introduction purposes. All rights belong to the copyright holders.

Book Information

• Unique ID: aae00a8c13d4e092
• File Extension: .pdf
• File Size: 24,382,956 bytes (23.253 MB)
• Title: –
• Author: Unknown
• ISBN: 9781668469033, 9781668469040, 9781668469057, 9781668477564, 9781668466872, 9781668471005, 9781668477663, 9781668475249, 9781668466971, 9781799870821, 9781668457221, 9781668442258, 9781799890591, 9781799891833, 9781799891215, 9781799883500, 9781799883678, 9781799881612, 9781799867210, 9781799877011, 9781799870104, 9781799871569, 9781799870784, 9781799875642, 9781799850403, 9781799857884, 9781799851011, 9781799836612, 9781799827641, 9781522593843, 9781799848851, 9781799841654, 9781799801221, 9781522598060, 9781799825845, 9781799812944, 9781799817185, 9781799816980, 9781799818632, 9781799811527, 9781799811923, 9781799821427, 9781522596592, 9781522576785, 9781522585398, 9781522592570, 9781522594482, 9781522577843, 9781522578796, 9781522577904, 9781522560296, 9781522538707, 9781522550204, 9781522536406, 9781522540779, 9781522550174, 9781522553144, 9781522527732, 9781522524311, 9781522531296, 9781522531852, 9781522528456, 9781522523857, 9781683180005, 9781522525318, 9781522523031, 9781683180166, 9781522519973, 9781522517214, 9781522507598, 9781522502876, 9781522501534, 9781466698345, 9781466698581, 9781466699168, 9781466688537, 9781466686762, 9781466688230, 9781466684935, 9781466685109, 9781466682108, 9781466682139, 9781466682252, 9781466674615, 9781466673120, 9781466664852, 9781466663596, 9781466661783, 9781466661943, 9781466662520, 9781466660984, 9781466660267, 9781466660342, 9781466657847, 9781466651821, 9781466648012, 9781466646599, 9781466646834, 9781466645226, 9781466645264, 9781466644946, 9781466641938, 9781466642171, 9781466642294, 9781466625334, 9781615209712, 9781609608279, 9781605666976, 9781615207039, 9783031015878, 9783031015885
• Pages: 518
• Language: English (en)

Reading & Word Statistics

• Estimated Reading Time: 481.95 minutes
• Total Words: 96,390
• Total Characters: 655,313
• Average Words per Page: 186.08
• Average Characters per Page: 1265.08

Most Frequent Words

graph (1747), networks (743), neural (721), data (582), network (512), learning (490), doi (478), gnns (452), node (392), graphs (357), nodes (349), gnn (347), information (347), model (290), used (289), conference (288), ieee (285), adversarial (238), attention (237), image (236), attacks (235), applications (230), models (230), detection (228), social (227), proceedings (220), prediction (218), international (217), between (210), deep (209), convolutional (205), classification (201), computer (198), science (197), using (197), recognition (197), systems (195), research (192), zhang (190), university (188), performance (184), based (180), edges (176), features (176), methods (168), training (166), machine (160), arxiv (158), figure (157), engineering (154), different (153), method (143), use (142), link (142), vision (141), processing (137), wang (133), analysis (132), one (132), structure (132), india (131), techniques (129), knowledge (129), representations (129), face (125), feature (123), technology (122), matrix (119), saliency (116), edge (114), reference (113), object (113), embedding (111), representation (111), also (109), isbn (109), tasks (109), copyright (108), price (106), images (105), transactions (104), several (96), layer (94), new (92), proposed (91), kumar (90), various (90), salient (90), including (89), approach (89), acm (88), pattern (87), two (87), input (87), number (84), gcnns (83), process (80), mining (79), visual (79), news (79).

PDF Download