Publication:
Towards node liability in federated learning: Computational cost and network overhead

Simple item page
dc.contributor.authorMalandrino, Francesco
dc.contributor.authorChiasserini, Carla Fabiana
dc.contributor.editorIEEE
dc.contributor.funderEuropean Commissionen
dc.date.accessioned2023-05-16T13:55:33Z
dc.date.available2022-02-24T11:25:40Z
dc.date.issued2021-09
dc.description.abstractMany machine learning (ML) techniques suf-fer from the drawback that their output (e.g., a classifi-cation decision) is not clearly and intuitively connected to their input (e.g., an image). To cope with this issue, several explainable ML techniques have been proposed to, e.g., identify which pixels of an input image had the strongest influence on its classification. However, in distributed scenarios, it is often more important to connect decisions with the information used for the model training and the nodes supplying such information. To this end, in this paper we focus on federated learning and present a new methodology, named node liability in federated learning (NL-FL), which permits to identify the source of the training information that most contributed to a given decision. After discussing NL-FL’s cost in terms of extra computation, storage, and network latency, we demonstrate its usefulness in an edge-based scenario. We find that NL-FL is able to swiftly identify misbehaving nodes and to exclude them from the training process, thereby improving learning accuracy.en
dc.description.sponsorshipThis work was supported through the EU 5Growth project (Grant No. 856709).en
dc.format.extent8
dc.identifier.bibliographicCitationMalandrino, Francesco; Chiasserini, Carla Fabiana. Towards node liability in federated learning: computational cost and network overhead. In: IEEE Communications Magazine, 59(9), Sep.2021, Pp. 72-77en
dc.identifier.doihttps://doi.org/10.1109/MCOM.011.2100231
dc.identifier.issn0163-6804
dc.identifier.publicationfirstpage1
dc.identifier.publicationfirstpage72
dc.identifier.publicationissue9
dc.identifier.publicationlastpage8
dc.identifier.publicationlastpage77
dc.identifier.publicationtitleIEEE Communications Magazineen
dc.identifier.publicationvolume59
dc.identifier.urihttps://hdl.handle.net/10016/34234
dc.language.isoengen
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/856709
dc.rights© 2021 IEEE.en
dc.rights.accessRightsopen accessen
dc.subject.ecienciaTelecomunicacioneses
dc.subject.otherTrainingen
dc.subject.otherCostsen
dc.subject.otherMachine learningen
dc.subject.otherCollaborative worken
dc.subject.otherComputational efficiencyen
dc.subject.otherServersen
dc.titleTowards node liability in federated learning: Computational cost and network overheaden
dc.typeresearch article*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Towards_CM_ps.pdf
Size:
510.58 KB
Format:
Adobe Portable Document Format
Download
Collections
OpenAIRE: Open Access Infrastructure for Research in Europe