國立虎尾科技大學 |

Learning, Privacy, and Reliable Communication in Large Data Networks.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Learning, Privacy, and Reliable Communication in Large Data Networks./
Author:	Fereydounian, Mohammad.
Description:	1 online resource (201 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-08, Section: A.
Contained By:	Dissertations Abstracts International85-08A.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798381510614

Learning, Privacy, and Reliable Communication in Large Data Networks.
Fereydounian, Mohammad.

Learning, Privacy, and Reliable Communication in Large Data Networks. - 1 online resource (201 pages)

Source: Dissertations Abstracts International, Volume: 85-08, Section: A.

Thesis (Ph.D.)--University of Pennsylvania, 2023.

Includes bibliographical references

This thesis explores advancements in three distinct domains: communications, privacy, and machine learning. Within the realm of communication, a comprehensive study is conducted on channel coding at low capacity, a critical aspect of Internet of Things (IoT) technology requiring reliable transmission over channels with minimal capacity. Despite existing finite-length analyses yielding inaccurate predictions and current coding schemes proving inefficient in low-capacity scenarios, this thesis addresses these limitations. It characterizes the finite-length fundamental limits of channel coding for essential channels, offering provably efficient code designs tailored for low-capacity environments. In the domain of privacy, attention is directed towards a decentralized consensus problem handled in a private manner. Existing methods for classical consensus problems often involve openly exchanging private information. This thesis proposes an algorithmic framework capable of achieving the exact limit and the fastest possible convergence rate while safeguarding the privacy of users' local values. Additionally, a novel information-theoretic metric is introduced to effectively measure the privacy of a node concerning another node within the network. In the machine learning domain, a rigorous mathematical framework is established to investigate the function class of Graph Neural Networks (GNNs) in relation to their initialization and internal estimators. Utilizing a unique technique for the algebraic representation of a multiset of vectors, termed Multiset Equivalent Function (MEF), it is demonstrated that GNNs can generate functions satisfying a weight-equipped variant of permutation-equivariance using distinct features. The MEF technique further reveals that GNNs, equipped with node identifiers in their initialization, can generate any function in a fully connected and weighted graph scenario. These findings contribute to a formal understanding of the intricate relationship between GNNs and other algorithmic procedures applied to graphs, such as min-cut value and shortest path problems, as well as the re-derivation of the known connection between GNNs and the Weisfeiler-Lehman graph-isomorphism test.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381510614Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Machine learningIndex Terms--Genre/Form:

554714
Electronic books.

Learning, Privacy, and Reliable Communication in Large Data Networks.
LDR:03607ntm a22003977 4500 001 1147345
005 20240909100803.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381510614
035 $a (MiAaPQ)AAI30818064
035 $a AAI30818064
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Fereydounian, Mohammad. $3 1473050
245 1 0 $a Learning, Privacy, and Reliable Communication in Large Data Networks.
264 0 $c 2023
300 $a 1 online resource (201 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-08, Section: A.
500 $a Advisor: Hassani, Hamed.
502 $a Thesis (Ph.D.)--University of Pennsylvania, 2023.
504 $a Includes bibliographical references
520 $a This thesis explores advancements in three distinct domains: communications, privacy, and machine learning. Within the realm of communication, a comprehensive study is conducted on channel coding at low capacity, a critical aspect of Internet of Things (IoT) technology requiring reliable transmission over channels with minimal capacity. Despite existing finite-length analyses yielding inaccurate predictions and current coding schemes proving inefficient in low-capacity scenarios, this thesis addresses these limitations. It characterizes the finite-length fundamental limits of channel coding for essential channels, offering provably efficient code designs tailored for low-capacity environments. In the domain of privacy, attention is directed towards a decentralized consensus problem handled in a private manner. Existing methods for classical consensus problems often involve openly exchanging private information. This thesis proposes an algorithmic framework capable of achieving the exact limit and the fastest possible convergence rate while safeguarding the privacy of users' local values. Additionally, a novel information-theoretic metric is introduced to effectively measure the privacy of a node concerning another node within the network. In the machine learning domain, a rigorous mathematical framework is established to investigate the function class of Graph Neural Networks (GNNs) in relation to their initialization and internal estimators. Utilizing a unique technique for the algebraic representation of a multiset of vectors, termed Multiset Equivalent Function (MEF), it is demonstrated that GNNs can generate functions satisfying a weight-equipped variant of permutation-equivariance using distinct features. The MEF technique further reveals that GNNs, equipped with node identifiers in their initialization, can generate any function in a fully connected and weighted graph scenario. These findings contribute to a formal understanding of the intricate relationship between GNNs and other algorithmic procedures applied to graphs, such as min-cut value and shortest path problems, as well as the re-derivation of the known connection between GNNs and the Weisfeiler-Lehman graph-isomorphism test.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Electrical engineering. $3 596380
650 4 $a Information science. $3 561178
653 $a Machine learning
653 $a Internet of Things
653 $a Multiset Equivalent Function
653 $a Graph Neural Networks
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
690 $a 0544
690 $a 0723
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Pennsylvania. $b Electrical and Systems Engineering. $3 1189698
773 0 $t Dissertations Abstracts International $g 85-08A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30818064 $z click for full text (PQDT)