Optimal Power Control for Over-the-Air Federated Learning with Gradient Compression
Federated Learning (FL) has emerged as a transformative approach in distributed machine learning, enabling the collaborative training of models using decentralized datasets from diverse sources such as mobile edge devices. This paradigm not only enhances data privacy but also significantly reduces t...
Gespeichert in:
| Veröffentlicht in: | Proceedings - International Conference on Parallel and Distributed Systems S. 326 - 333 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Tagungsbericht |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
10.10.2024
|
| Schlagworte: | |
| ISSN: | 2690-5965 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Federated Learning (FL) has emerged as a transformative approach in distributed machine learning, enabling the collaborative training of models using decentralized datasets from diverse sources such as mobile edge devices. This paradigm not only enhances data privacy but also significantly reduces the communication burden typically associated with centralized data aggregation. In wireless networks, Over-the-air Federated Learning (OTA-FL) has been developed as a communication-efficient solution, allowing for the simultaneous transmission and aggregation of model updates from numerous edge devices across the available bandwidth. Gradient compression techniques are necessary to further enhance the communication efficiency of FL, particularly in bandwidth-constrained wireless environments. Despite these advancements, OTA-FL with gradient compression encounters substantial challenges, including learning performance degradation due to compression errors, non-uniform channel fading, and noise interference. Existing power control strategies have yet to fully address these issues, leaving a significant gap in optimizing OTA-FL performance under gradient compression. This paper introduces a novel power control strategy that coordinately integrates gradient compression to optimize OTAFL performance by minimizing the impact of channel fading and noise. Our approach employs linear approximations to complex terms, ensuring the stability and effectiveness of each gradient descent iteration. Numerical results demonstrate that our strategy significantly enhances convergence rates compared to traditional methods like channel inversion and uniform power transmission. This research advances the OTA-FL field and opens new avenues for performance tuning in communication-efficient federated learning systems. |
|---|---|
| AbstractList | Federated Learning (FL) has emerged as a transformative approach in distributed machine learning, enabling the collaborative training of models using decentralized datasets from diverse sources such as mobile edge devices. This paradigm not only enhances data privacy but also significantly reduces the communication burden typically associated with centralized data aggregation. In wireless networks, Over-the-air Federated Learning (OTA-FL) has been developed as a communication-efficient solution, allowing for the simultaneous transmission and aggregation of model updates from numerous edge devices across the available bandwidth. Gradient compression techniques are necessary to further enhance the communication efficiency of FL, particularly in bandwidth-constrained wireless environments. Despite these advancements, OTA-FL with gradient compression encounters substantial challenges, including learning performance degradation due to compression errors, non-uniform channel fading, and noise interference. Existing power control strategies have yet to fully address these issues, leaving a significant gap in optimizing OTA-FL performance under gradient compression. This paper introduces a novel power control strategy that coordinately integrates gradient compression to optimize OTAFL performance by minimizing the impact of channel fading and noise. Our approach employs linear approximations to complex terms, ensuring the stability and effectiveness of each gradient descent iteration. Numerical results demonstrate that our strategy significantly enhances convergence rates compared to traditional methods like channel inversion and uniform power transmission. This research advances the OTA-FL field and opens new avenues for performance tuning in communication-efficient federated learning systems. |
| Author | Li, Yunhe Zhang, Weizhou Song, Linqi Ruan, Mengzhe Xu, Weitao |
| Author_xml | – sequence: 1 givenname: Mengzhe surname: Ruan fullname: Ruan, Mengzhe email: cs.mzr@my.cityu.edu.hk organization: City University of Hong Kong Shenzhen Research Institute – sequence: 2 givenname: Yunhe surname: Li fullname: Li, Yunhe email: yunheli4-c@my.cityu.edu.hk organization: City University of Hong Kong Shenzhen Research Institute – sequence: 3 givenname: Weizhou surname: Zhang fullname: Zhang, Weizhou email: weizhouz@u.nus.edu organization: Institute of Operations Research and Analytics, National University of Singapore – sequence: 4 givenname: Linqi surname: Song fullname: Song, Linqi email: linqi.song@cityu.edu.hk organization: City University of Hong Kong Shenzhen Research Institute – sequence: 5 givenname: Weitao surname: Xu fullname: Xu, Weitao email: weitaoxu@cityu.edu.hk organization: City University of Hong Kong Shenzhen Research Institute |
| BookMark | eNotj11LwzAYRqMouM39A5H8gc43SfN1Waqbg8IG0-vRNW9dZEtLGhz--xX06nluzoEzJXehC0jIM4MFY2Bf1uW2eN0pISQsOPB8AQASbsjcamuEYJJJq9QtmXBlIRu_fCDTYfgG4DAyE7Lb9Mmf6xPddheMtOxCit2Jtl2kmx-MWTpiVvhIl-gw1gkdrbCOwYcvevHpSFexdh5DGslzH3EYfBceyX1bnwac_--MfC7fPsr3rNqs1mVRZZ5plTJUaB2iaG0LKIHlSiuXC2VMw407NGOUbUXDhGSqcfYAmhkttDNa5-zgQMzI05_XI-K-j2NH_N0z0EpozsUV4ptSzA |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/ICPADS63350.2024.00050 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISBN | 9798331515966 |
| EISSN | 2690-5965 |
| EndPage | 333 |
| ExternalDocumentID | 10763722 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Innovation and Technology Commission funderid: 10.13039/501100003452 – fundername: National Natural Science Foundation of China funderid: 10.13039/501100001809 |
| GroupedDBID | 29O 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IPLJI OCL RIE RIL RNS |
| ID | FETCH-LOGICAL-i176t-e6e9dee3f9f0e5014676d43688c28dbc3359f3c13516cd9b0718737d87741bd03 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001481011800040&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 01:59:30 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i176t-e6e9dee3f9f0e5014676d43688c28dbc3359f3c13516cd9b0718737d87741bd03 |
| PageCount | 8 |
| ParticipantIDs | ieee_primary_10763722 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-Oct.-10 |
| PublicationDateYYYYMMDD | 2024-10-10 |
| PublicationDate_xml | – month: 10 year: 2024 text: 2024-Oct.-10 day: 10 |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings - International Conference on Parallel and Distributed Systems |
| PublicationTitleAbbrev | ICPADS |
| PublicationYear | 2024 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0020350 |
| Score | 2.2773945 |
| Snippet | Federated Learning (FL) has emerged as a transformative approach in distributed machine learning, enabling the collaborative training of models using... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 326 |
| SubjectTerms | Fading channels Federated learning Gradient Compression Linear approximation Noise Numerical stability Over-the-Air Computation Power control Power transmission Stability analysis Tuning Wireless networks |
| Title | Optimal Power Control for Over-the-Air Federated Learning with Gradient Compression |
| URI | https://ieeexplore.ieee.org/document/10763722 |
| WOSCitedRecordID | wos001481011800040&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELUAMTCVjyK-5YHVYMdt7IxVocDSRipI3arEvqBKkKKQ8vu5c9LCwsBmeYilc8737Lt7j7FrKaHnTT8XkcqIVFsrYbNCC6VMgQEISKo8iE2Y8djOZknaNquHXhgACMVncEPDkMv3S7eipzL0cPQGE-GJu22MaZq1NrcrSpG1LcBKJrdPw3RwN401zuItMCKObEnN9b80VEIIGXX-ufg-6_404_F0E2YO2BaUh6yzVmPgrXMesekEvf89e-MpCZ_xYVODzhGU8gn-rwKRnhgsKj4i-ghEmJ633KqvnB5j-UMVqr9qTp9uqmPLLnsZ3T8PH0UrmSAWysS1gBgSD6CLpJBAKcPYxJ5I5q2LrM8dmiMptCNZvtj5JEeAYY023iIKVLmX-pjtlMsSThhHVzfe2yLKZdaDHJEEDpzyEPVzg8jilHXJSPOPhhVjvrbP2R_z52yP9oHOfSUv2E5dreCS7bqvevFZXYW9_AYrq58N |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVQQYKpfBTxjQdWg52kcTJWhdKK0kZqkbpVcXxBlSBFIeX3c5ekhYWBzfKQSOdc7tm-9x5jN1KCZ3XbCEfFJKrtKhHEqSuU0ikWICCr8tJsQo9GwWwWRjVZveTCAEDZfAa3NCzv8u0yWdFRGWY4ZoN28I-73fY8R1V0rc3-ii7JahKwkuHdoBt17ie-i7O4D3RIJVsSvf6Xi0pZRHrNf75-n7V-6Hg82hSaA7YF2SFrrv0YeJ2eR2wyxvx_j994RNZnvFt1oXOEpXyMX6xArCc6i5z3SEACMabltbrqK6fjWP6Yl_1fBadHV_2xWYu99B6m3b6oTRPEQmm_EOBDaAHcNEwl0KWhr31LMvNB4gTWJBiOMHUTMubzExsahBiBdrUNEAcqY6V7zBrZMoMTxjHZtbVB6hgZe2AQS-AgURacttGILU5Zi4I0_6h0Mebr-Jz9MX_NdvvT5-F8OBg9nbM9WhOqAkpesEaRr-CS7SRfxeIzvyrX9RuhG6JU |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+-+International+Conference+on+Parallel+and+Distributed+Systems&rft.atitle=Optimal+Power+Control+for+Over-the-Air+Federated+Learning+with+Gradient+Compression&rft.au=Ruan%2C+Mengzhe&rft.au=Li%2C+Yunhe&rft.au=Zhang%2C+Weizhou&rft.au=Song%2C+Linqi&rft.date=2024-10-10&rft.pub=IEEE&rft.eissn=2690-5965&rft.spage=326&rft.epage=333&rft_id=info:doi/10.1109%2FICPADS63350.2024.00050&rft.externalDocID=10763722 |