Fed2: Feature-Aligned Federated Learning

Simple item page
dc.contributor.authorYu, Fuxun
dc.contributor.authorZhang, Weishan
dc.contributor.authorQin, Zhuwei
dc.contributor.authorXu, Zirui
dc.contributor.authorWang, Di
dc.contributor.authorLiu, Chenchen
dc.contributor.authorTian, Zhi
dc.contributor.authorChen, Xiang
dc.date.accessioned2021-08-24T18:28:15Z
dc.date.available2021-08-24T18:28:15Z
dc.date.issued2021-08-14
dc.descriptionKDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, August 14–18, 2021, Virtual Event, Singaporeen_US
dc.description.abstractFederated learning learns from scattered data by fusing collaborative models from local nodes. However, conventional coordinate-based model averaging by FedAvg ignored the random information encoded per parameter and may suffer from structural feature misalignment. In this work, we propose Fed2, a feature-aligned federated learning framework to resolve this issue by establishing a firm structure-feature alignment across the collaborative models. Fed2 is composed of two major designs: First, we design a feature-oriented model structure adaptation method to ensure explicit feature allocation in different neural network structures. Applying the structure adaptation to collaborative models, matchable structures with similar feature information can be initialized at the very early training stage. During the federated learning process, we then propose a feature paired averaging scheme to guarantee aligned feature distribution and maintain no feature fusion conflicts under either IID or non-IID scenarios. Eventually, Fed2 could effectively enhance the federated learning convergence performance under extensive homo- and heterogeneous settings, providing excellent convergence speed, accuracy, and computation/communication efficiency.en_US
dc.description.urihttps://dl.acm.org/doi/abs/10.1145/3447548.3467309en_US
dc.format.extent9 pagesen_US
dc.genreconference papers and proceedingsen_US
dc.identifierdoi:10.13016/m270pu-u2on
dc.identifier.citationYu, Fuxun et al.; Fed2: Feature-Aligned Federated Learning; KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 14 August 2021, Pages 2066–2074; https://doi.org/10.1145/3447548.3467309en_US
dc.identifier.urihttps://doi.org/10.1145/3447548.3467309
dc.identifier.urihttp://hdl.handle.net/11603/22658
dc.language.isoen_USen_US
dc.publisherAssociation for Computing Machineryen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.en_US
dc.subjectneural networksen_US
dc.subjectfederated learningen_US
dc.subjectinterpretabilityen_US
dc.titleFed2: Feature-Aligned Federated Learningen_US
dc.typeTexten_US
dcterms.creatorhttps://orcid.org/0000-0001-7749-0640en_US

Files

License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection