poster

Poster: Stackelberg Game-based Model Partition and Resource Allocation in Split Federated Learning

Authors:

Victor C. M. LeungAuthors Info & Claims

SENSYS '24: Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems

Pages 877 - 878

https://doi.org/10.1145/3666025.3699416

Published: 04 November 2024 Publication History

Get Access

Abstract

This paper investigates dynamic model partitioning and resource allocation in split federated learning, aiming to maximize the utility of clients and the Central Server (CS). We first model the interactions between the CS and clients as a Stackelberg game, where the CS acts as the leader to set payment and allocate computation resources, while clients as followers to determine model partitioning strategies. Then, we transform the problem into a bi-level optimization and propose a Nash-Equilibrium-based Stackelberg Algorithm (NESA) to solve it. Finally, the experimental results indicate that a Stackelberg equilibrium exists between the CS and clients, and NESA achieves higher utility and improves accuracy and convergence speed.

References

[1]

Dong Jun Han, Do Yeon Kim, Minseok Choi, Christopher G. Brinton, and Jaekyun Moon, "SplitGP: Achieving Both Generalization and Personalization in Federated Learning," in Proc. IEEE INFOCOM, 2023, pp. 1--10.

Google Scholar

[2]

Huan Zhou, Zhenning Wang, Nan Cheng, Deze Zeng, and Pingzhi Fan, "Stackelberg-Game-Based Computation Offloading Method in Cloud-Edge Computing Networks," IEEE Internet of Things Journal, vol. 9, no. 17, pp. 16510--16520, 2022.

Crossref

Google Scholar

Index Terms

Poster: Stackelberg Game-based Model Partition and Resource Allocation in Split Federated Learning
1. Theory of computation
  1. Models of computation

Recommendations

Load balancing model based on Stackelberg game for multi-homing in heterogeneous radio access networks
ICAIT '08: Proceedings of the 2008 International Conference on Advanced Infocomm Technology

We address the problem of load balancing for multi-homing in heterogeneous radio access networks, where multiple wireless access networks compete with each other to offer bandwidth. We firstly have presented a Stackelberg game-theoretic model for ...
A Stackelberg game-based approach for interactions among Internet service providers and content providers
Abstract
This paper studies non-neutral market share where Internet service providers (ISPs) charge content providers (CPs) for the content delivery. Each provider seeks to maximize its own profit by determining its price and their service qualities (...
Joint Pricing and Power Allocation for Dynamic Spectrum Access Networks with Stackelberg Game Model

In this work we study joint pricing and power allocation for Dynamic Spectrum Access (DSA) networks with Stackelberg game. In our model, Primary User (PU) is the game leader and jointly determines its power allocation (to guarantee its QoS requirement) ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

SenSys '24: Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems

November 2024

950 pages

ISBN:9798400706974

DOI:10.1145/3666025

Chair:
Jie Liu,
Co-chairs:
Yuanchao Shu,
Jiming Chen,
Program Chair:
Yuan He,
Program Co-chair:
Rui Tan

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s).

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 04 November 2024

Check for updates

Author Tags

Qualifiers

Poster

Funding Sources

National Natural Science Foundation of China

Conference

SenSys '24

Sponsor:

SenSys '24: 22nd ACM Conference on Embedded Networked Sensor Systems

November 4 - 7, 2024

Hangzhou, China

Acceptance Rates

Overall Acceptance Rate 174 of 867 submissions, 20%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
78
Total Downloads

Downloads (Last 12 months)78
Downloads (Last 6 weeks)78

Reflects downloads up to 11 Dec 2024

Other Metrics

View Author Metrics

Citations

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Index Terms

Recommendations

Load balancing model based on Stackelberg game for multi-homing in heterogeneous radio access networks

A Stackelberg game-based approach for interactions among Internet service providers and content providers

Joint Pricing and Power Allocation for Dynamic Spectrum Access Networks with Stackelberg Game Model