FedPD : Federated Open Set Recognition with Parameter Disentanglement

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

2 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Place of PublicationLos Alamitos, Calif.
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Pages4882-4891
ISBN (electronic)979-8-3503-0718-4
ISBN (print)979-8-3503-0719-1
Publication statusPublished - Oct 2023

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499
ISSN (electronic)2380-7504

Conference

TitleIEEE International Conference on Computer Vision 2023 (ICCV 2023)
LocationParis Convention Center
PlaceFrance
CityParis
Period2 - 6 October 2023

Abstract

Existing federated learning (FL) approaches are deployed under the unrealistic closed-set setting, with both training and testing classes belong to the same set, which makes the global model fail to identify the unseen classes asunknown'. To this end, we aim to study a novel problem of federated open-set recognition (FedOSR), which learns an open-set recognition (OSR) model under federated paradigm such that it classifies seen classes while at the same time detects unknown classes. In this work, we propose a parameter disentanglement guided federated open-set recognition (FedPD) algorithm to address two core challenges of FedOSR: cross-client inter-set interference between learning closed-set and open-set knowledge and cross-client intra-set inconsistency by data heterogeneity. The proposed FedPD framework mainly leverages two modules, ie, local parameter disentanglement (LPD) and global divide-and-conquer aggregation (GDCA), to first disentangle client OSR model into different subnetworks, then align the corresponding parts cross clients for matched model aggregation. Specifically, on the client side, LPD decouples an OSR model into a closed-set subnetwork and an open-set subnetwork by the task-related importance, thus preventing inter-set interference. On the server side, GDCA first partitions the two subnetworks into specific and shared parts, and subsequently aligns the corresponding parts through optimal transport to eliminate parameter misalignment. Extensive experiments on various datasets demonstrate the superior performance of our proposed method.

Citation Format(s)

FedPD: Federated Open Set Recognition with Parameter Disentanglement. / Yang, Chen; Zhu, Meilu; Liu, Yifan et al.
Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023. Los Alamitos, Calif.: Institute of Electrical and Electronics Engineers, Inc., 2023. p. 4882-4891 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review