File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Broadband Analog Aggregation for Low-Latency Federated Edge Learning

TitleBroadband Analog Aggregation for Low-Latency Federated Edge Learning
Authors
KeywordsComputational modeling
Wireless communication
Broadband communication
Signal to noise ratio
Servers
Issue Date2020
PublisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7693
Citation
IEEE Transactions on Wireless Communications, 2020, v. 19 n. 1, p. 491-506 How to Cite?
AbstractTo leverage rich data distributed at the network edge, a new machine-learning paradigm, called edge learning, has emerged where learning algorithms are deployed at the edge for providing intelligent services to mobile users. While computing speeds are advancing rapidly, the communication latency is becoming the bottleneck of fast edge learning. To address this issue, this work is focused on designing a low-latency multi-access scheme for edge learning. To this end, we consider a popular privacy-preserving framework, federated edge learning (FEEL), where a global AI-model at an edge-server is updated by aggregating (averaging) local models trained at edge devices. It is proposed that the updates simultaneously transmitted by devices over broadband channels should be analog aggregated “over-the-air” by exploiting the waveform-superposition property of a multi-access channel. Such broadband analog aggregation (BAA) results in dramatical communication-latency reduction compared with the conventional orthogonal access (i.e., OFDMA). In this work, the effects of BAA on learning performance are quantified targeting a single-cell random network. First, we derive two tradeoffs between communication-and-learning metrics, which are useful for network planning and optimization. The power control (“truncated channel inversion”) required for BAA results in a tradeoff between the update-reliability [as measured by the receive signal-to-noise ratio (SNR)] and the expected update-truncation ratio. Consider the scheduling of cell-interior devices to constrain path loss. This gives rise to the other tradeoff between the receive SNR and fraction of data exploited in learning. Next, the latency-reduction ratio of the proposed BAA with respect to the traditional OFDMA scheme is proved to scale almost linearly with the device population. Experiments based on a neural network and a real dataset are conducted for corroborating the theoretical results.
Persistent Identifierhttp://hdl.handle.net/10722/290570
ISSN
2023 Impact Factor: 8.9
2023 SCImago Journal Rankings: 5.371
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorHuang, K-
dc.contributor.authorWang, Y-
dc.contributor.authorZhu, G-
dc.date.accessioned2020-11-02T05:44:07Z-
dc.date.available2020-11-02T05:44:07Z-
dc.date.issued2020-
dc.identifier.citationIEEE Transactions on Wireless Communications, 2020, v. 19 n. 1, p. 491-506-
dc.identifier.issn1536-1276-
dc.identifier.urihttp://hdl.handle.net/10722/290570-
dc.description.abstractTo leverage rich data distributed at the network edge, a new machine-learning paradigm, called edge learning, has emerged where learning algorithms are deployed at the edge for providing intelligent services to mobile users. While computing speeds are advancing rapidly, the communication latency is becoming the bottleneck of fast edge learning. To address this issue, this work is focused on designing a low-latency multi-access scheme for edge learning. To this end, we consider a popular privacy-preserving framework, federated edge learning (FEEL), where a global AI-model at an edge-server is updated by aggregating (averaging) local models trained at edge devices. It is proposed that the updates simultaneously transmitted by devices over broadband channels should be analog aggregated “over-the-air” by exploiting the waveform-superposition property of a multi-access channel. Such broadband analog aggregation (BAA) results in dramatical communication-latency reduction compared with the conventional orthogonal access (i.e., OFDMA). In this work, the effects of BAA on learning performance are quantified targeting a single-cell random network. First, we derive two tradeoffs between communication-and-learning metrics, which are useful for network planning and optimization. The power control (“truncated channel inversion”) required for BAA results in a tradeoff between the update-reliability [as measured by the receive signal-to-noise ratio (SNR)] and the expected update-truncation ratio. Consider the scheduling of cell-interior devices to constrain path loss. This gives rise to the other tradeoff between the receive SNR and fraction of data exploited in learning. Next, the latency-reduction ratio of the proposed BAA with respect to the traditional OFDMA scheme is proved to scale almost linearly with the device population. Experiments based on a neural network and a real dataset are conducted for corroborating the theoretical results.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7693-
dc.relation.ispartofIEEE Transactions on Wireless Communications-
dc.rightsIEEE Transactions on Wireless Communications. Copyright © Institute of Electrical and Electronics Engineers.-
dc.rights©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectComputational modeling-
dc.subjectWireless communication-
dc.subjectBroadband communication-
dc.subjectSignal to noise ratio-
dc.subjectServers-
dc.titleBroadband Analog Aggregation for Low-Latency Federated Edge Learning-
dc.typeArticle-
dc.identifier.emailHuang, K: huangkb@eee.hku.hk-
dc.identifier.authorityHuang, K=rp01875-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TWC.2019.2946245-
dc.identifier.scopuseid_2-s2.0-85078333591-
dc.identifier.hkuros318112-
dc.identifier.volume19-
dc.identifier.issue1-
dc.identifier.spage491-
dc.identifier.epage506-
dc.identifier.isiWOS:000508384000036-
dc.publisher.placeUnited States-
dc.identifier.issnl1536-1276-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats