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

e-Archivo Repository

Show simple item record Malandrino, Francesco Chiasserini, Carla Fabiana 2022-02-24T11:25:40Z 2022-02-24T11:25:40Z 2022-02-24
dc.identifier.issn 0163-6804
dc.description.abstract Many 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.
dc.description.sponsorship This work was supported through the EU 5Growth project (Grant No. 856709).
dc.format.extent 8
dc.language.iso eng
dc.rights © 2021/2022 IEEE. This work has been submitted to the IEEE for possible publication in IEEE Communications Magazine. Copyright may be transferred without notice, after which this version may no longer be accessible.
dc.title Towards node liability in federated learning: Computational cost and network overhead
dc.type article
dc.subject.eciencia Telecomunicaciones
dc.rights.accessRights openAccess
dc.relation.projectID info:eu-repo/grantAgreement/EC/856709
dc.type.version submittedVersion
dc.identifier.publicationfirstpage 1
dc.identifier.publicationlastpage 8
dc.identifier.publicationtitle IEEE Communications Magazine
dc.contributor.funder European Commission
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record