TY - GEN
T1 - Federated Clustering with Unknown Number of Clusters
AU - Zou, Rong
AU - Zhang, Yunfan
AU - Zhang, Yiqun
AU - Lu, Yang
AU - Li, Mengke
AU - Cheung, Yiu Ming
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China (NSFC) under grants: 62102097, 62376233, and 62306181, NSFC/Research Grants Council (RGC) Joint Research Scheme under grant N_HKBU214/21, General Research Fund of RGC under grants: 12201321, 12202622, and 12201323, Natural Science Foundation of Guangdong Province under grants: 2023A1515012855 and 2024A1515010163, RGC Senior Research Fellow Scheme under grant SRFS2324-2S02, Shenzhen Science and Technology Program under grant RCBS20231211090659101, and the Xiaomi Young Talents program.
Publisher Copyright:
© 2024 IEEE
PY - 2024/8/16
Y1 - 2024/8/16
N2 - Federated clustering is crucial to mining knowledge from unlabeled data distributed to multiple clients while preserving privacy. As there is no explicit learning supervision, clustering is considered a challenging federated learning task. Most existing works assume that the 'true' cluster number k∗ is given to each client and server, which is far from a real federated learning scenario. Without the guidance of k∗, federated clustering becomes more challenging, rendering most existing solutions infeasible. We therefore propose a Federated Competitive and Cooperative Learning mechanism (FedCCL) to explore and fuse heterogeneous cluster distributions from clients automatically, and eventually form a global cluster partition, without requiring the cluster number to be given. We let the clients download seed points to explore their local distributions, which are then uploaded to the server for fusion. Different clients are allowed to compete on a single seed to form a consensus, while close seeds cooperate to represent a cluster. By iteratively homogenizing the cooperated seeds, a proper number of clusters will gradually emerge. Extensive experiments demonstrate the effectiveness of the proposed method.
AB - Federated clustering is crucial to mining knowledge from unlabeled data distributed to multiple clients while preserving privacy. As there is no explicit learning supervision, clustering is considered a challenging federated learning task. Most existing works assume that the 'true' cluster number k∗ is given to each client and server, which is far from a real federated learning scenario. Without the guidance of k∗, federated clustering becomes more challenging, rendering most existing solutions infeasible. We therefore propose a Federated Competitive and Cooperative Learning mechanism (FedCCL) to explore and fuse heterogeneous cluster distributions from clients automatically, and eventually form a global cluster partition, without requiring the cluster number to be given. We let the clients download seed points to explore their local distributions, which are then uploaded to the server for fusion. Different clients are allowed to compete on a single seed to form a consensus, while close seeds cooperate to represent a cluster. By iteratively homogenizing the cooperated seeds, a proper number of clusters will gradually emerge. Extensive experiments demonstrate the effectiveness of the proposed method.
KW - Competitive and Coopera-tive Learning
KW - Federated Clustering
KW - Unknown Number of Clusters
UR - http://www.scopus.com/inward/record.url?scp=85207828356&partnerID=8YFLogxK
U2 - 10.1109/DOCS63458.2024.10704350
DO - 10.1109/DOCS63458.2024.10704350
M3 - Conference proceeding
AN - SCOPUS:85207828356
SN - 9798350377859
T3 - International Conference on Data-Driven Optimization of Complex Systems
SP - 671
EP - 677
BT - 2024 6th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2024
PB - IEEE
T2 - 6th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2024
Y2 - 16 August 2024 through 18 August 2024
ER -