Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Over-the-Air Computation for Machine Learning: Model Aggregation via Retransmissions
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Network and Systems Engineering.ORCID iD: 0000-0002-5761-2580
2022 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

With the emerging Internet of Things (IoT) paradigm, more than a billion sensing devices will be collecting an unprecedented amount of data. Simultaneously, the field of data analytics is being revolutionized by modern machine learning (ML) techniques that enable sophisticated processing of massive datasets. Many researchers are envisioning a combination of these two technologies to support exciting applications such as environmental monitoring, Industry 4.0, and vehicular communications. However, traditional wireless communication protocols are inefficient in supporting distributed ML services, where data and computations are distributed over wireless networks. This motivates the need for new wireless communication methods. One such method, over-the-air computation (AirComp), promises to communicate with massive gains in terms of energy, latency, and spectrum efficiency compared to traditional methods.

The expected efficiency of AirComp is due to the complete spectrum sharing for all participating devices. Unlike in traditional physical-layer communications, where interference is avoided by allocating orthogonal communication channels, AirComp promotes interference to compute a function of the individually transmitted messages. However, AirComp can not reconstruct functions perfectly but introduces errors in the process, which harms the convergence rate and region of optimality of ML algorithms. The main objective of this thesis is to develop methods that reduce these errors and analyze their effects on ML performance.

In the first part of this thesis, we consider the general problem of designing wireless methods for ML applications. In particular, we present an extensive survey which divides the field into two broad categories, digital communications and analog over-the-air-computation. Digital communications refers to orthogonal communication schemes that are optimized for ML metrics, such as classification accuracy, privacy, and data-importance, rather than traditional communication metrics such as fairness, data rate, and reliability. Analog over-the-air-computation refers to the AirComp method and its application to distributed ML, where communication-efficiency, function estimation, and privacy are key concerns.

In the second part of this thesis, we focus on the analog over-the-air computation problem. We consider a network setup with multiple devices and a server that can be reached via a single hop, where the wireless channel is modeled as a multiple-access channel with fading and additive noise. Over such a channel, the AirComp function estimate is associated with two types of error: 1) misalignment errors caused by channel fading and 2) noise-induced errors caused by the additive noise. To mitigate these errors, we propose AirComp with retransmissions and develop the optimal power control scheme for such a system. Furthermore, we use optimization theory to derive bounds on the convergence of an AirComp-supported ML system that reveal a relationship between the number of retransmissions and loss of the ML model. Finally, with numerical results we show that retransmissions can significantly improve ML performance, especially for low-SNR scenarios. 

Abstract [sv]

Med Internet of Things (IoT)-paradigmen, kommer över en miljard sensorenheter att samla en mängd data som saknar motstycke. Samtidigt har dataanalys revolutionerats av moderna maskininlärningstekniker (ML) som möjliggör avancerad behandling av massiva dataset. Många forskare föreställer sig en kombination av dessa två two teknologier för att möjliggöra spännande applikationer som miljöövervakning, Industri 4.0, och fordonskommunikation. Tyvärr är traditionella kommunikationsprotokoll ineffektiva när det kommer till att stödja distribuerad maskininlärning, där data och beräkningar är utspridda över trådlösa nätverk. Detta motiverar behovet av nya trådlösa kommunikationsprotokoll. Ett protokoll, over-the-air computation (AirComp), lovar att kommunicera med enorma fördelar när det kommer till energieffektivitet, latens, and spektrumeffektivitet jämfört med traditionella protkoll.

AirComps effektivitet beror på den fullständiga spektrumdelningen mellan alla medverkande enheter. Till skillnad från traditionell ortogonal kommunikation, där interferens undviks genom att allokera ortogonala radioresurser, så uppmuntrar AirComp interferens och nyttjar den för att räkna ut en funktion av de kommunicerade meddelanderna. Dock kan inte AirComp rekonstruera funktioner perfekt, utan introducerar fel i processen vilket försämrar konvergensen av ML-algoritmer. Det huvudsakliga målet med den här avhandlingen är att utveckla metoder som minskar dessa fel och att analysera de effekter felen har på prestandan av distribuerade ML-algoritmer.

I den första delen av avhandlingen behandlar vi det allmänna problemet med att designa trådlösa nätverksprotokoll för att stödja ML. Specifikt så presenterar vi en utförlig kartläggning som delar upp fältet i två kategorier, digital kommunikation och analog AirComp. Digital kommunikation syftar på ortogonala kommunikationsprotokoll som är optimerade för ML-måttstockar, t.ex. klassifikationskapabilitet, integritet, och data-vikt (data-importance), snarare än traditionella kommunikationsmål såsom jämlikhet, datahastighet, och tillförlitlighet. Analog AirComp syftar till AirComps applicering till distribuerad ML, där kommunikationseffektivitet, funktionsestimering, och integritet är viktiga måttstockar.

I den andra delen av avhandlingen fokuserar vi på det analoga AirComp-problemet. Vi beaktar ett nätverk med flera enheter och en server som kan nås via en länk, där den trådlösa kanalen modelleras som en multiple-access kanal (MAC) med fädning och additivt brus. Över en sådan kanal så associeras AirComps funktionsestimat med två sorters fel: 1) felinställningsfel orsakade av fädning och 2) brusinducerade fel orsakade av det additiva bruset. För att mildra felen föreslår vi AirComp med återsändning och utvecklar den optimala "power control"-algoritmen för ett sådant system. Dessutom använder vi optimeringsteori för att härleda begränsningar på konvergensen av ett AirCompsystem för distribuerad ML som tydliggör ett förhållande mellan antalet återsändningar och förlustfunktionen för ML-modellen. Slutligen visar vi att återsändningar kan signifikant förbättra ML-prestanda genom numeriska resultat, särskilt när signal-till-brus ration är låg. 

Place, publisher, year, edition, pages
Stockholm, Sweden: KTH Royal Institute of Technology, 2022. , p. 197
Series
TRITA-EECS-AVL ; 2022:51
Keywords [en]
Wireless Communications, Machine Learning, Over-the-Air Computation, Federated Learning
National Category
Communication Systems
Research subject
Electrical Engineering
Identifiers
URN: urn:nbn:se:kth:diva-317315ISBN: 978-91-8040-325-2 (print)OAI: oai:DiVA.org:kth-317315DiVA, id: diva2:1694369
Presentation
2022-11-04, D31, Stockholm, 09:30 (English)
Opponent
Supervisors
Note

QC 20220909

Available from: 2022-09-09 Created: 2022-09-09 Last updated: 2022-10-28Bibliographically approved
List of papers
1. Unbiased Over-the-Air Computation via Retransmissions
Open this publication in new window or tab >>Unbiased Over-the-Air Computation via Retransmissions
(English)Manuscript (preprint) (Other academic)
National Category
Telecommunications
Identifiers
urn:nbn:se:kth:diva-316991 (URN)
Note

QC 20220905

Available from: 2022-09-02 Created: 2022-09-02 Last updated: 2022-09-09Bibliographically approved
2. Federated Learning Over-the-Air by Retransmissions
Open this publication in new window or tab >>Federated Learning Over-the-Air by Retransmissions
(English)Manuscript (preprint) (Other academic)
National Category
Telecommunications
Identifiers
urn:nbn:se:kth:diva-316990 (URN)
Note

QC 20220905

Available from: 2022-09-02 Created: 2022-09-02 Last updated: 2022-09-09Bibliographically approved
3. Over-the-Air Federated Learning with Retransmissions
Open this publication in new window or tab >>Over-the-Air Federated Learning with Retransmissions
2021 (English)Conference paper, Published paper (Refereed)
National Category
Telecommunications
Identifiers
urn:nbn:se:kth:diva-312444 (URN)10.1109/SPAWC51858.2021.9593119 (DOI)000783745500059 ()2-s2.0-85120029196 (Scopus ID)
Conference
IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)
Note

QC 20220520

Available from: 2022-05-18 Created: 2022-05-18 Last updated: 2022-09-23Bibliographically approved
4. Wireless for Machine Learning: A Survey
Open this publication in new window or tab >>Wireless for Machine Learning: A Survey
Show others...
2022 (English)In: Foundations and Trends in Signal Processing, ISSN 1932-8346, Vol. 15, no 4, p. 290-399Article, review/survey (Refereed) Accepted
Abstract [en]

As data generation increasingly takes place on devices withouta wired connection, Machine Learning (ML) related traffic willbe ubiquitous in wireless networks. Many studies have shownthat traditional wireless protocols are highly inefficient or unsustainableto support ML, which creates the need for new wirelesscommunication methods. In this monograph, we give a comprehensivereview of the state-of-the-art wireless methods that arespecifically designed to support ML services over distributeddatasets. Currently, there are two clear themes within the literature,analog over-the-air computation and digital radio resourcemanagement optimized for ML. This survey gives an introductionto these methods, reviews the most important works, highlightsopen problems, and discusses application scenarios.

Place, publisher, year, edition, pages
Now Publishers Inc., 2022
Keywords
wireless communications, machine learning, federated learning, resource allocation
National Category
Telecommunications
Research subject
Electrical Engineering
Identifiers
urn:nbn:se:kth:diva-313006 (URN)10.1561/2000000114 (DOI)
Note

QC 20220610

Available from: 2022-05-27 Created: 2022-05-27 Last updated: 2024-03-15Bibliographically approved

Open Access in DiVA

Licentiatavhandling_Sammanfattning(1063 kB)787 downloads
File information
File name FULLTEXT01.pdfFile size 1063 kBChecksum SHA-512
859a9c43b004ab7ba9f91adf09243e5a7a506293368359fb668cd1ae1145ff71eb3006cc6594a7ab65830fbe020ba3d0af12b2063d299d0caa8200a737cee220
Type fulltextMimetype application/pdf

Other links

for online defense

Search in DiVA

By author/editor
Hellström, Henrik
By organisation
Network and Systems Engineering
Communication Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 788 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 807 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf