Joint Client Selection and Task Assignment for Multi-Task Federated Learning in MEC Networks

In this paper, we investigate the multi-task federated learning in mobile edge computing (MEC) networks where a central server assigns different federated learning tasks to different MEC servers and select feasible clients to participate in the federated learning training process. The problem is for...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2021 IEEE Global Communications Conference (GLOBECOM) s. 1 - 6
Hlavní autoři: Cheng, Zhipeng, Min, Minghui, Liwang, Minghui, Gao, Zhibin, Huang, Lianfen
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.12.2021
Témata:
Client selection
Clustering algorithms
Collaborative work
MEC
multi-task federated learning
Multitasking
Search problems
Simulation
task assignment
Three-dimensional displays
Training
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we investigate the multi-task federated learning in mobile edge computing (MEC) networks where a central server assigns different federated learning tasks to different MEC servers and select feasible clients to participate in the federated learning training process. The problem is formulated as a joint client selection and task assignment problem to maximize the total utility of all tasks, subject to the trained model quality and total training latency. Since the above-mentioned problem is NP-Hard, it poses challenges to obtain the optimal solution within polynomial time, the problem is transformed into a many-to-one-to-one 3D matching problem. To further reduce the computation while ensuring the matching stability, we first adopt the spectral clustering algorithm to cluster the clients into multiple client clusters. Then we reformulate the problem as a 3-Partite weighted hypergraph total weight maximization problem. Finally, we propose a greedy and local search (GLS) based algorithm to resolve the problem. Simulation results demonstrate the effectiveness of the proposed algorithm as compared with baseline schemes.
DOI:10.1109/GLOBECOM46510.2021.9685698